time=2026-01-04T07:20:10.447-06:00 level=INFO source=routes.go:1564 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:DEBUG OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/nic/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2026-01-04T07:20:10.449-06:00 level=INFO source=images.go:493 msg="total blobs: 20"
time=2026-01-04T07:20:10.449-06:00 level=INFO source=images.go:500 msg="total unused blobs removed: 0"
time=2026-01-04T07:20:10.450-06:00 level=INFO source=routes.go:1617 msg="Listening on 127.0.0.1:11434 (version 0.13.5-9-gd087e46-dirty)"
time=2026-01-04T07:20:10.450-06:00 level=DEBUG source=sched.go:120 msg="starting llm scheduler"
time=2026-01-04T07:20:10.451-06:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2026-01-04T07:20:10.452-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 46387"
time=2026-01-04T07:20:10.452-06:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_DEBUG=1 PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/bin:/usr/lib/llvm/21/bin:/usr/lib/llvm/20/bin:/opt/cuda/bin:/home/nic/.local/bin:/home/nic/bin LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends OLLAMA_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends
time=2026-01-04T07:20:10.806-06:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=355.728112ms OLLAMA_LIBRARY_PATH="[/usr/lib64/ollama /usr/lib64/ollama/backends]" extra_envs=map[]
time=2026-01-04T07:20:10.807-06:00 level=DEBUG source=runner.go:124 msg="evaluating which, if any, devices to filter out" initial_count=2
time=2026-01-04T07:20:10.807-06:00 level=DEBUG source=runner.go:146 msg="verifying if device is supported" library=/usr/lib64/ollama/backends description="NVIDIA GeForce RTX 3080" compute=8.6 id=GPU-81cc0f98-96b6-0d33-bfa1-5989f1d84393 pci_id=0000:01:00.0
time=2026-01-04T07:20:10.807-06:00 level=DEBUG source=runner.go:146 msg="verifying if device is supported" library=/usr/lib64/ollama/backends description="NVIDIA GeForce RTX 3080" compute=8.6 id=GPU-81cc0f98-96b6-0d33-bfa1-5989f1d84393 pci_id=0000:01:00.0
time=2026-01-04T07:20:10.807-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 33883"
time=2026-01-04T07:20:10.807-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 39937"
time=2026-01-04T07:20:10.807-06:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_DEBUG=1 PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/bin:/usr/lib/llvm/21/bin:/usr/lib/llvm/20/bin:/opt/cuda/bin:/home/nic/.local/bin:/home/nic/bin LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends OLLAMA_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends CUDA_VISIBLE_DEVICES=GPU-81cc0f98-96b6-0d33-bfa1-5989f1d84393 GGML_CUDA_INIT=1
time=2026-01-04T07:20:10.807-06:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_DEBUG=1 PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/bin:/usr/lib/llvm/21/bin:/usr/lib/llvm/20/bin:/opt/cuda/bin:/home/nic/.local/bin:/home/nic/bin LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends OLLAMA_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends CUDA_VISIBLE_DEVICES=GPU-81cc0f98-96b6-0d33-bfa1-5989f1d84393 GGML_CUDA_INIT=1
time=2026-01-04T07:20:11.119-06:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=312.625227ms OLLAMA_LIBRARY_PATH="[/usr/lib64/ollama /usr/lib64/ollama/backends]" extra_envs="map[CUDA_VISIBLE_DEVICES:GPU-81cc0f98-96b6-0d33-bfa1-5989f1d84393 GGML_CUDA_INIT:1]"
time=2026-01-04T07:20:11.126-06:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=319.222076ms OLLAMA_LIBRARY_PATH="[/usr/lib64/ollama /usr/lib64/ollama/backends]" extra_envs="map[CUDA_VISIBLE_DEVICES:GPU-81cc0f98-96b6-0d33-bfa1-5989f1d84393 GGML_CUDA_INIT:1]"
time=2026-01-04T07:20:11.126-06:00 level=DEBUG source=runner.go:40 msg="GPU bootstrap discovery took" duration=675.629328ms
time=2026-01-04T07:20:11.126-06:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-81cc0f98-96b6-0d33-bfa1-5989f1d84393 filter_id="" library=CUDA compute=8.6 name=CUDA0 description="NVIDIA GeForce RTX 3080" libdirs="" driver=13.1 pci_id=0000:01:00.0 type=discrete total="10.0 GiB" available="8.7 GiB"
time=2026-01-04T07:20:11.126-06:00 level=INFO source=routes.go:1658 msg="entering low vram mode" "total vram"="10.0 GiB" threshold="20.0 GiB"
[GIN] 2026/01/04 - 07:20:38 | 200 |      53.005µs |       127.0.0.1 | HEAD     "/"
time=2026-01-04T07:20:38.080-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=general.alignment default=32
[GIN] 2026/01/04 - 07:20:38 | 200 |   16.359509ms |       127.0.0.1 | POST     "/api/show"
time=2026-01-04T07:20:38.103-06:00 level=DEBUG source=runner.go:264 msg="refreshing free memory"
time=2026-01-04T07:20:38.104-06:00 level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
time=2026-01-04T07:20:38.104-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 33835"
time=2026-01-04T07:20:38.104-06:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_DEBUG=1 PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/bin:/usr/lib/llvm/21/bin:/usr/lib/llvm/20/bin:/opt/cuda/bin:/home/nic/.local/bin:/home/nic/bin LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends OLLAMA_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends
time=2026-01-04T07:20:38.472-06:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=368.658431ms OLLAMA_LIBRARY_PATH="[/usr/lib64/ollama /usr/lib64/ollama/backends]" extra_envs=map[]
time=2026-01-04T07:20:38.472-06:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=368.866495ms
time=2026-01-04T07:20:38.473-06:00 level=DEBUG source=sched.go:194 msg="updating default concurrency" OLLAMA_MAX_LOADED_MODELS=3 gpu_count=1
time=2026-01-04T07:20:38.478-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=general.alignment default=32
time=2026-01-04T07:20:38.478-06:00 level=DEBUG source=sched.go:211 msg="loading first model" model=/home/nic/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6
time=2026-01-04T07:20:38.493-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=general.alignment default=32
time=2026-01-04T07:20:38.493-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
time=2026-01-04T07:20:38.493-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=true
time=2026-01-04T07:20:38.493-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.separator_token_id default=0
time=2026-01-04T07:20:38.493-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=nomic-bert.moe_every_n_layers default=0
time=2026-01-04T07:20:38.493-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=nomic-bert.normalize_embeddings default=false
time=2026-01-04T07:20:38.493-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=nomic-bert.expert_count default=0
time=2026-01-04T07:20:38.493-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=nomic-bert.expert_used_count default=0
time=2026-01-04T07:20:38.494-06:00 level=WARN source=server.go:167 msg="requested context size too large for model" num_ctx=8192 n_ctx_train=2048
time=2026-01-04T07:20:38.494-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --model /home/nic/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6 --port 42767"
time=2026-01-04T07:20:38.494-06:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_DEBUG=1 PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/bin:/usr/lib/llvm/21/bin:/usr/lib/llvm/20/bin:/opt/cuda/bin:/home/nic/.local/bin:/home/nic/bin LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends OLLAMA_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends
time=2026-01-04T07:20:38.494-06:00 level=INFO source=sched.go:443 msg="system memory" total="23.4 GiB" free="17.7 GiB" free_swap="60.7 GiB"
time=2026-01-04T07:20:38.494-06:00 level=INFO source=sched.go:450 msg="gpu memory" id=GPU-81cc0f98-96b6-0d33-bfa1-5989f1d84393 library=CUDA available="8.3 GiB" free="8.7 GiB" minimum="457.0 MiB" overhead="0 B"
time=2026-01-04T07:20:38.494-06:00 level=INFO source=server.go:755 msg="loading model" "model layers"=13 requested=-1
time=2026-01-04T07:20:38.507-06:00 level=INFO source=runner.go:1405 msg="starting ollama engine"
time=2026-01-04T07:20:38.510-06:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:42767"
time=2026-01-04T07:20:38.516-06:00 level=INFO source=runner.go:1278 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Disabled KvSize:2048 KvCacheType: NumThreads:6 GPULayers:13[ID:GPU-81cc0f98-96b6-0d33-bfa1-5989f1d84393 Layers:13(0..12)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-01-04T07:20:38.528-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=general.alignment default=32
time=2026-01-04T07:20:38.528-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=general.description default=""
time=2026-01-04T07:20:38.528-06:00 level=INFO source=ggml.go:136 msg="" architecture=nomic-bert file_type=F16 name=nomic-embed-text-v1.5 description="" num_tensors=112 num_key_values=25
time=2026-01-04T07:20:38.528-06:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib64/ollama
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 3080, compute capability 8.6, VMM: yes, ID: GPU-81cc0f98-96b6-0d33-bfa1-5989f1d84393
load_backend: loaded CUDA backend from /usr/lib64/ollama/libggml-cuda.so
load_backend: loaded CPU backend from /usr/lib64/ollama/libggml-cpu-x64.so
time=2026-01-04T07:20:38.728-06:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib64/ollama/backends
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 3080, compute capability 8.6, VMM: yes, ID: GPU-81cc0f98-96b6-0d33-bfa1-5989f1d84393
load_backend: loaded CUDA backend from /usr/lib64/ollama/backends/libggml-cuda.so
load_backend: loaded CPU backend from /usr/lib64/ollama/backends/libggml-cpu-x64.so
time=2026-01-04T07:20:38.736-06:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CPU.2.LLAMAFILE=1 CUDA.0.ARCHS=860 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 CUDA.1.ARCHS=860 CUDA.1.USE_GRAPHS=1 CUDA.1.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc)
time=2026-01-04T07:20:38.737-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
time=2026-01-04T07:20:38.737-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=true
time=2026-01-04T07:20:38.737-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.separator_token_id default=0
time=2026-01-04T07:20:38.737-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=nomic-bert.moe_every_n_layers default=0
time=2026-01-04T07:20:38.737-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=nomic-bert.normalize_embeddings default=false
time=2026-01-04T07:20:38.737-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=nomic-bert.expert_count default=0
time=2026-01-04T07:20:38.737-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=nomic-bert.expert_used_count default=0
time=2026-01-04T07:20:38.738-06:00 level=WARN source=runner.go:1213 msg="model does not support caching, setting batch size to context length" batch_size=2048
time=2026-01-04T07:20:39.007-06:00 level=DEBUG source=ggml.go:852 msg="compute graph" nodes=371 splits=4
time=2026-01-04T07:20:39.021-06:00 level=DEBUG source=ggml.go:852 msg="compute graph" nodes=371 splits=2
time=2026-01-04T07:20:39.022-06:00 level=DEBUG source=device.go:240 msg="model weights" device=CUDA0 size="260.9 MiB"
time=2026-01-04T07:20:39.022-06:00 level=DEBUG source=device.go:245 msg="model weights" device=CPU size="44.7 MiB"
time=2026-01-04T07:20:39.022-06:00 level=DEBUG source=device.go:262 msg="compute graph" device=CUDA0 size="256.0 MiB"
time=2026-01-04T07:20:39.022-06:00 level=DEBUG source=device.go:267 msg="compute graph" device=CPU size="6.0 MiB"
time=2026-01-04T07:20:39.022-06:00 level=DEBUG source=device.go:272 msg="total memory" size="567.6 MiB"
time=2026-01-04T07:20:39.022-06:00 level=DEBUG source=server.go:780 msg=memory success=true required.InputWeights=46894080 required.CPU.Graph=6291456 required.CUDA0.ID=GPU-81cc0f98-96b6-0d33-bfa1-5989f1d84393 required.CUDA0.Weights="[18886656 18886656 18886656 18886656 18886656 18886656 18886656 18886656 18886656 18886656 18886656 18886656 46881792]" required.CUDA0.Graph=268435456
time=2026-01-04T07:20:39.022-06:00 level=DEBUG source=server.go:974 msg="available gpu" id=GPU-81cc0f98-96b6-0d33-bfa1-5989f1d84393 library=CUDA "available layer vram"="8.0 GiB" backoff=0.00 minimum="457.0 MiB" overhead="0 B" graph="256.0 MiB"
time=2026-01-04T07:20:39.022-06:00 level=DEBUG source=server.go:791 msg="new layout created" layers="13[ID:GPU-81cc0f98-96b6-0d33-bfa1-5989f1d84393 Layers:13(0..12)]"
time=2026-01-04T07:20:39.022-06:00 level=INFO source=runner.go:1278 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Disabled KvSize:2048 KvCacheType: NumThreads:6 GPULayers:13[ID:GPU-81cc0f98-96b6-0d33-bfa1-5989f1d84393 Layers:13(0..12)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-01-04T07:20:39.030-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=general.alignment default=32
time=2026-01-04T07:20:39.032-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
time=2026-01-04T07:20:39.032-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=true
time=2026-01-04T07:20:39.032-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.separator_token_id default=0
time=2026-01-04T07:20:39.032-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=nomic-bert.moe_every_n_layers default=0
time=2026-01-04T07:20:39.032-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=nomic-bert.normalize_embeddings default=false
time=2026-01-04T07:20:39.032-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=nomic-bert.expert_count default=0
time=2026-01-04T07:20:39.032-06:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=nomic-bert.expert_used_count default=0
time=2026-01-04T07:20:39.033-06:00 level=WARN source=runner.go:1213 msg="model does not support caching, setting batch size to context length" batch_size=2048
time=2026-01-04T07:20:39.037-06:00 level=DEBUG source=ggml.go:852 msg="compute graph" nodes=371 splits=4
time=2026-01-04T07:20:39.039-06:00 level=DEBUG source=ggml.go:852 msg="compute graph" nodes=371 splits=2
time=2026-01-04T07:20:39.039-06:00 level=DEBUG source=device.go:240 msg="model weights" device=CUDA0 size="260.9 MiB"
time=2026-01-04T07:20:39.039-06:00 level=DEBUG source=device.go:245 msg="model weights" device=CPU size="44.7 MiB"
time=2026-01-04T07:20:39.039-06:00 level=DEBUG source=device.go:262 msg="compute graph" device=CUDA0 size="256.0 MiB"
time=2026-01-04T07:20:39.039-06:00 level=DEBUG source=device.go:267 msg="compute graph" device=CPU size="6.0 MiB"
time=2026-01-04T07:20:39.039-06:00 level=DEBUG source=device.go:272 msg="total memory" size="567.6 MiB"
time=2026-01-04T07:20:39.039-06:00 level=DEBUG source=server.go:780 msg=memory success=true required.InputWeights=46894080 required.CPU.Graph=6291456 required.CUDA0.ID=GPU-81cc0f98-96b6-0d33-bfa1-5989f1d84393 required.CUDA0.Weights="[18886656 18886656 18886656 18886656 18886656 18886656 18886656 18886656 18886656 18886656 18886656 18886656 46881792]" required.CUDA0.Graph=268435456
time=2026-01-04T07:20:39.039-06:00 level=DEBUG source=server.go:974 msg="available gpu" id=GPU-81cc0f98-96b6-0d33-bfa1-5989f1d84393 library=CUDA "available layer vram"="8.0 GiB" backoff=0.00 minimum="457.0 MiB" overhead="0 B" graph="256.0 MiB"
time=2026-01-04T07:20:39.039-06:00 level=DEBUG source=server.go:791 msg="new layout created" layers="13[ID:GPU-81cc0f98-96b6-0d33-bfa1-5989f1d84393 Layers:13(0..12)]"
time=2026-01-04T07:20:39.040-06:00 level=INFO source=runner.go:1278 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Disabled KvSize:2048 KvCacheType: NumThreads:6 GPULayers:13[ID:GPU-81cc0f98-96b6-0d33-bfa1-5989f1d84393 Layers:13(0..12)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-01-04T07:20:39.040-06:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="260.9 MiB"
time=2026-01-04T07:20:39.040-06:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="44.7 MiB"
time=2026-01-04T07:20:39.040-06:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="256.0 MiB"
time=2026-01-04T07:20:39.040-06:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="6.0 MiB"
time=2026-01-04T07:20:39.040-06:00 level=INFO source=device.go:272 msg="total memory" size="567.6 MiB"
time=2026-01-04T07:20:39.040-06:00 level=INFO source=sched.go:517 msg="loaded runners" count=1
time=2026-01-04T07:20:39.040-06:00 level=INFO source=server.go:1347 msg="waiting for llama runner to start responding"
time=2026-01-04T07:20:39.040-06:00 level=INFO source=ggml.go:482 msg="offloading 12 repeating layers to GPU"
time=2026-01-04T07:20:39.040-06:00 level=INFO source=ggml.go:489 msg="offloading output layer to GPU"
time=2026-01-04T07:20:39.040-06:00 level=INFO source=ggml.go:494 msg="offloaded 13/13 layers to GPU"
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d540 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2721015c00 dst1=0x7f2721015c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721015c00 p_off=50420736 size=131072 end_off=50551808 OOB=0
[GGML-CUDA-DIAG] cuCtxGetCurrent BAD cr=0 CUDA_SUCCESS no error ctx=(nil)
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e000000 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] cuMemGetAddressRange FAILED cr=201 CUDA_ERROR_INVALID_CONTEXT invalid device context p=0x7f271e000000
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d540 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2721015c00 dst1=0x7f2721035c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721035c00 p_off=50551808 size=131072 end_off=50682880 OOB=0
[GGML-CUDA-DIAG] cuCtxGetCurrent BAD cr=0 CUDA_SUCCESS no error ctx=(nil)
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720cb5c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] cuMemGetAddressRange FAILED cr=201 CUDA_ERROR_INVALID_CONTEXT invalid device context p=0x7f2720cb5c00
[GGML-CUDA-DIAG] cuCtxGetCurrent BAD cr=0 CUDA_SUCCESS no error ctx=(nil)
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f27215b5c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] cuMemGetAddressRange FAILED cr=201 CUDA_ERROR_INVALID_CONTEXT invalid device context p=0x7f27215b5c00
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d540 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2721015c00 dst1=0x7f2721055c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721055c00 p_off=50682880 size=131072 end_off=50813952 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e020000 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e020000 p_off=131072 size=131072 end_off=262144 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720cd5c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720cd5c00 p_off=47012864 size=131072 end_off=47143936 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d540 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2721015c00 dst1=0x7f2721075c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721075c00 p_off=50813952 size=131072 end_off=50945024 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f27215d5c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27215d5c00 p_off=56450048 size=131072 end_off=56581120 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d540 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2721015c00 dst1=0x7f2721095c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721095c00 p_off=50945024 size=131072 end_off=51076096 OOB=0
time=2026-01-04T07:20:39.041-06:00 level=INFO source=server.go:1381 msg="waiting for server to become available" status="llm server loading model"
time=2026-01-04T07:20:39.041-06:00 level=DEBUG source=server.go:1391 msg="model load progress 0.00"
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f27215f5c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27215f5c00 p_off=56581120 size=131072 end_off=56712192 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720cf5c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720cf5c00 p_off=47143936 size=131072 end_off=47275008 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e040000 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e040000 p_off=262144 size=131072 end_off=393216 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f2721615c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720d15c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720d15c00 p_off=47275008 size=131072 end_off=47406080 OOB=0
[GGML-CUDA-DIAG] cuCtxGetCurrent BAD cr=0 CUDA_SUCCESS no error ctx=(nil)
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721a35c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] cuMemGetAddressRange FAILED cr=201 CUDA_ERROR_INVALID_CONTEXT invalid device context p=0x7f2721a35c00
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d540 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2721015c00 dst1=0x7f27210b5c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27210b5c00 p_off=51076096 size=131072 end_off=51207168 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720d35c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720d35c00 p_off=47406080 size=131072 end_off=47537152 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721a55c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721a55c00 p_off=61168640 size=131072 end_off=61299712 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721615c00 p_off=56712192 size=131072 end_off=56843264 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e060000 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d540 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2721015c00 dst1=0x7f27210d5c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27210d5c00 p_off=51207168 size=131072 end_off=51338240 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e060000 p_off=393216 size=131072 end_off=524288 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720d55c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720d55c00 p_off=47537152 size=131072 end_off=47668224 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721a75c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721a75c00 p_off=61299712 size=131072 end_off=61430784 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f2721635c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721635c00 p_off=56843264 size=131072 end_off=56974336 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d540 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2721015c00 dst1=0x7f27210f5c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27210f5c00 p_off=51338240 size=131072 end_off=51469312 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720d75c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720d75c00 p_off=47668224 size=131072 end_off=47799296 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721a95c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721a95c00 p_off=61430784 size=131072 end_off=61561856 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e080000 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f2721655c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] cuCtxGetCurrent BAD cr=0 CUDA_SUCCESS no error ctx=(nil)
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e080000 p_off=524288 size=131072 end_off=655360 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f2721135c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] cuMemGetAddressRange FAILED cr=201 CUDA_ERROR_INVALID_CONTEXT invalid device context p=0x7f2721135c00
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d540 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2721015c00 dst1=0x7f2721115c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721115c00 p_off=51469312 size=131072 end_off=51600384 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721655c00 p_off=56974336 size=131072 end_off=57105408 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720d95c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720d95c00 p_off=47799296 size=131072 end_off=47930368 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721ab5c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721ab5c00 p_off=61561856 size=131072 end_off=61692928 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e0a0000 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e0a0000 p_off=655360 size=131072 end_off=786432 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f2721155c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721155c00 p_off=51731456 size=131072 end_off=51862528 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720db5c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720db5c00 p_off=47930368 size=131072 end_off=48061440 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721ad5c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721ad5c00 p_off=61692928 size=131072 end_off=61824000 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f2721675c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721675c00 p_off=57105408 size=131072 end_off=57236480 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720dd5c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720dd5c00 p_off=48061440 size=131072 end_off=48192512 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f2721175c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721175c00 p_off=51862528 size=131072 end_off=51993600 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721af5c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721af5c00 p_off=61824000 size=131072 end_off=61955072 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f2721695c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721695c00 p_off=57236480 size=131072 end_off=57367552 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800db00 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2721eb5c00 dst1=0x7f2721eb5c00 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721eb5c00 p_off=65756160 size=3072 end_off=65759232 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720df5c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720df5c00 p_off=48192512 size=131072 end_off=48323584 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f2721195c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721195c00 p_off=51993600 size=131072 end_off=52124672 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721b15c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721b15c00 p_off=61955072 size=131072 end_off=62086144 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e0c0000 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e0c0000 p_off=786432 size=131072 end_off=917504 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f27216b5c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27216b5c00 p_off=57367552 size=131072 end_off=57498624 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800dc70 buffer=0x7f27b94d3ab0 data(host)=0xc000830000 dst0=0x7f2721eb6800 dst1=0x7f2721eb6800 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721eb6800 p_off=65759232 size=3072 end_off=65762304 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720e15c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720e15c00 p_off=48323584 size=131072 end_off=48454656 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800dde0 buffer=0x7f27b94d3ab0 data(host)=0xc000850000 dst0=0x7f2721eb7400 dst1=0x7f2721eb7400 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721eb7400 p_off=65762304 size=3072 end_off=65765376 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720e35c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720e35c00 p_off=48454656 size=131072 end_off=48585728 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721b35c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721b35c00 p_off=62086144 size=131072 end_off=62217216 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f27216d5c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27216d5c00 p_off=57498624 size=131072 end_off=57629696 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f27211b5c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27211b5c00 p_off=52124672 size=131072 end_off=52255744 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720e55c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720e55c00 p_off=48585728 size=131072 end_off=48716800 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f27216f5c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27216f5c00 p_off=57629696 size=131072 end_off=57760768 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f27211d5c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27211d5c00 p_off=52255744 size=131072 end_off=52386816 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720e75c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720e75c00 p_off=48716800 size=131072 end_off=48847872 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f2721715c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721715c00 p_off=57760768 size=131072 end_off=57891840 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f27211f5c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27211f5c00 p_off=52386816 size=131072 end_off=52517888 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720e95c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720e95c00 p_off=48847872 size=131072 end_off=48978944 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e0e0000 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e0e0000 p_off=917504 size=131072 end_off=1048576 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f2721735c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721735c00 p_off=57891840 size=131072 end_off=58022912 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f2721215c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721215c00 p_off=52517888 size=131072 end_off=52648960 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720eb5c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720eb5c00 p_off=48978944 size=131072 end_off=49110016 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f2721755c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721755c00 p_off=58022912 size=131072 end_off=58153984 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f2721235c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721235c00 p_off=52648960 size=131072 end_off=52780032 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e100000 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e100000 p_off=1048576 size=131072 end_off=1179648 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720ed5c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720ed5c00 p_off=49110016 size=131072 end_off=49241088 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f2721775c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721775c00 p_off=58153984 size=131072 end_off=58285056 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f2721255c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721255c00 p_off=52780032 size=131072 end_off=52911104 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720ef5c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720ef5c00 p_off=49241088 size=131072 end_off=49372160 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f2721275c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721275c00 p_off=52911104 size=131072 end_off=53042176 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e120000 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e120000 p_off=1179648 size=131072 end_off=1310720 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720f15c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720f15c00 p_off=49372160 size=131072 end_off=49503232 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f2721295c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721295c00 p_off=53042176 size=131072 end_off=53173248 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f2721795c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721795c00 p_off=58285056 size=131072 end_off=58416128 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721b55c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721b55c00 p_off=62217216 size=131072 end_off=62348288 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720f35c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720f35c00 p_off=49503232 size=131072 end_off=49634304 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e140000 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e140000 p_off=1310720 size=131072 end_off=1441792 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721b75c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721b75c00 p_off=62348288 size=131072 end_off=62479360 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720f55c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720f55c00 p_off=49634304 size=131072 end_off=49765376 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721b95c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721b95c00 p_off=62479360 size=131072 end_off=62610432 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e160000 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e160000 p_off=1441792 size=131072 end_off=1572864 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f27212b5c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27212b5c00 p_off=53173248 size=131072 end_off=53304320 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720f75c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720f75c00 p_off=49765376 size=131072 end_off=49896448 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f27217b5c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27217b5c00 p_off=58416128 size=131072 end_off=58547200 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f27212d5c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27212d5c00 p_off=53304320 size=131072 end_off=53435392 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720f95c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720f95c00 p_off=49896448 size=131072 end_off=50027520 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f27212f5c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27212f5c00 p_off=53435392 size=131072 end_off=53566464 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720fb5c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720fb5c00 p_off=50027520 size=131072 end_off=50158592 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f2721315c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721315c00 p_off=53566464 size=131072 end_off=53697536 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f27217d5c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27217d5c00 p_off=58547200 size=131072 end_off=58678272 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f2721335c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721335c00 p_off=53697536 size=131072 end_off=53828608 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800df50 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f2721eb8000 dst1=0x7f2721eb8000 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721eb8000 p_off=65765376 size=3072 end_off=65768448 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e180000 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e180000 p_off=1572864 size=131072 end_off=1703936 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f27217f5c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27217f5c00 p_off=58678272 size=131072 end_off=58809344 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f2721355c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721355c00 p_off=53828608 size=131072 end_off=53959680 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720fd5c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720fd5c00 p_off=50158592 size=131072 end_off=50289664 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e1a0000 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e1a0000 p_off=1703936 size=131072 end_off=1835008 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f2721815c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721815c00 p_off=58809344 size=131072 end_off=58940416 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f2721eb8c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721eb8c00 p_off=65768448 size=131072 end_off=65899520 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f2721375c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721375c00 p_off=53959680 size=131072 end_off=54090752 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721bb5c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721bb5c00 p_off=62610432 size=131072 end_off=62741504 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d3d0 buffer=0x7f27b94d3ab0 data(host)=0xc00070e000 dst0=0x7f2720cb5c00 dst1=0x7f2720ff5c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720ff5c00 p_off=50289664 size=131072 end_off=50420736 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e1c0000 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e1c0000 p_off=1835008 size=131072 end_off=1966080 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f2721395c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721395c00 p_off=54090752 size=131072 end_off=54221824 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721bd5c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721bd5c00 p_off=62741504 size=131072 end_off=62872576 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f27213b5c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27213b5c00 p_off=54221824 size=131072 end_off=54352896 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e1e0000 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e1e0000 p_off=1966080 size=131072 end_off=2097152 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721bf5c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721bf5c00 p_off=62872576 size=131072 end_off=63003648 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f2721ed8c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721ed8c00 p_off=65899520 size=131072 end_off=66030592 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e230 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2722218c00 dst1=0x7f2722218c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f27213d5c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f2721835c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721835c00 p_off=58940416 size=131072 end_off=59071488 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27213d5c00 p_off=54352896 size=131072 end_off=54483968 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e200000 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e200000 p_off=2097152 size=131072 end_off=2228224 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721c15c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721c15c00 p_off=63003648 size=131072 end_off=63134720 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f2721ef8c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721ef8c00 p_off=66030592 size=131072 end_off=66161664 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f2721855c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721855c00 p_off=59071488 size=131072 end_off=59202560 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f27213f5c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27213f5c00 p_off=54483968 size=131072 end_off=54615040 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722218c00 p_off=69307392 size=131072 end_off=69438464 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e220000 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e220000 p_off=2228224 size=131072 end_off=2359296 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721c35c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721c35c00 p_off=63134720 size=131072 end_off=63265792 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f2721f18c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721f18c00 p_off=66161664 size=131072 end_off=66292736 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f2721415c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721415c00 p_off=54615040 size=131072 end_off=54746112 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f2721875c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721875c00 p_off=59202560 size=131072 end_off=59333632 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e240000 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e240000 p_off=2359296 size=131072 end_off=2490368 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e230 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2722218c00 dst1=0x7f2722238c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722238c00 p_off=69438464 size=131072 end_off=69569536 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721c55c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721c55c00 p_off=63265792 size=131072 end_off=63396864 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f2721895c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721895c00 p_off=59333632 size=131072 end_off=59464704 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e260000 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e260000 p_off=2490368 size=131072 end_off=2621440 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f2721435c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721435c00 p_off=54746112 size=131072 end_off=54877184 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e230 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2722218c00 dst1=0x7f2722258c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722258c00 p_off=69569536 size=131072 end_off=69700608 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721c75c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721c75c00 p_off=63396864 size=131072 end_off=63527936 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f2721f38c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721f38c00 p_off=66292736 size=131072 end_off=66423808 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e280000 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e280000 p_off=2621440 size=131072 end_off=2752512 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f2721455c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721455c00 p_off=54877184 size=131072 end_off=55008256 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e230 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2722218c00 dst1=0x7f2722278c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722278c00 p_off=69700608 size=131072 end_off=69831680 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721c95c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721c95c00 p_off=63527936 size=131072 end_off=63659008 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f2721f58c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721f58c00 p_off=66423808 size=131072 end_off=66554880 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e2a0000 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e2a0000 p_off=2752512 size=131072 end_off=2883584 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f2721475c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721475c00 p_off=55008256 size=131072 end_off=55139328 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e230 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2722218c00 dst1=0x7f2722298c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722298c00 p_off=69831680 size=131072 end_off=69962752 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721cb5c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721cb5c00 p_off=63659008 size=131072 end_off=63790080 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f2721f78c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721f78c00 p_off=66554880 size=131072 end_off=66685952 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e2c0000 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e2c0000 p_off=2883584 size=131072 end_off=3014656 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e230 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2722218c00 dst1=0x7f27222b8c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27222b8c00 p_off=69962752 size=131072 end_off=70093824 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f2721495c00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721495c00 p_off=55139328 size=131072 end_off=55270400 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721cd5c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721cd5c00 p_off=63790080 size=131072 end_off=63921152 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f2721f98c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721f98c00 p_off=66685952 size=131072 end_off=66817024 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f27214b5c00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27214b5c00 p_off=55270400 size=131072 end_off=55401472 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e230 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2722218c00 dst1=0x7f27222d8c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27222d8c00 p_off=70093824 size=131072 end_off=70224896 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721cf5c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f27218b5c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e2e0000 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721cf5c00 p_off=63921152 size=131072 end_off=64052224 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e2e0000 p_off=3014656 size=131072 end_off=3145728 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f27214d5c00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27214d5c00 p_off=55401472 size=131072 end_off=55532544 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e230 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2722218c00 dst1=0x7f27222f8c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27222f8c00 p_off=70224896 size=131072 end_off=70355968 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e300000 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e300000 p_off=3145728 size=131072 end_off=3276800 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f2721fb8c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721fb8c00 p_off=66817024 size=131072 end_off=66948096 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f27214f5c00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27214f5c00 p_off=55532544 size=131072 end_off=55663616 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27218b5c00 p_off=59464704 size=131072 end_off=59595776 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721d15c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721d15c00 p_off=64052224 size=131072 end_off=64183296 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e230 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2722218c00 dst1=0x7f2722318c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722318c00 p_off=70355968 size=131072 end_off=70487040 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e320000 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e320000 p_off=3276800 size=131072 end_off=3407872 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f2721515c00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721515c00 p_off=55663616 size=131072 end_off=55794688 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f27218d5c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27218d5c00 p_off=59595776 size=131072 end_off=59726848 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721d35c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721d35c00 p_off=64183296 size=131072 end_off=64314368 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f2721535c00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721535c00 p_off=55794688 size=131072 end_off=55925760 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f27218f5c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27218f5c00 p_off=59726848 size=131072 end_off=59857920 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e340000 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e340000 p_off=3407872 size=131072 end_off=3538944 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f2722338c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722338c00 p_off=70487040 size=131072 end_off=70618112 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f2721555c00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721555c00 p_off=55925760 size=131072 end_off=56056832 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721d55c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721d55c00 p_off=64314368 size=131072 end_off=64445440 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f2721915c00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721915c00 p_off=59857920 size=131072 end_off=59988992 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e360000 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e360000 p_off=3538944 size=131072 end_off=3670016 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f2722358c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722358c00 p_off=70618112 size=131072 end_off=70749184 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721d75c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721d75c00 p_off=64445440 size=131072 end_off=64576512 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f2721935c00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721935c00 p_off=59988992 size=131072 end_off=60120064 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f2721575c00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721575c00 p_off=56056832 size=131072 end_off=56187904 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f2722378c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722378c00 p_off=70749184 size=131072 end_off=70880256 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721d95c00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f2721fd8c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721d95c00 p_off=64576512 size=131072 end_off=64707584 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721fd8c00 p_off=66948096 size=131072 end_off=67079168 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d6b0 buffer=0x7f27b94d3ab0 data(host)=0xc00072e000 dst0=0x7f2721135c00 dst1=0x7f2721595c00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721595c00 p_off=56187904 size=131072 end_off=56318976 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f2722398c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722398c00 p_off=70880256 size=131072 end_off=71011328 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721db5c00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721db5c00 p_off=64707584 size=131072 end_off=64838656 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f27223b8c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27223b8c00 p_off=71011328 size=131072 end_off=71142400 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f2721ff8c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721ff8c00 p_off=67079168 size=131072 end_off=67210240 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e380000 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e380000 p_off=3670016 size=131072 end_off=3801088 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f27227b8c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27227b8c00 p_off=75205632 size=131072 end_off=75336704 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f2721955c00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721955c00 p_off=60120064 size=131072 end_off=60251136 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f27223d8c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27223d8c00 p_off=71142400 size=131072 end_off=71273472 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f27227d8c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27227d8c00 p_off=75336704 size=131072 end_off=75467776 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f2721975c00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721975c00 p_off=60251136 size=131072 end_off=60382208 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e3a0000 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e3a0000 p_off=3801088 size=131072 end_off=3932160 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721dd5c00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721dd5c00 p_off=64838656 size=131072 end_off=64969728 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f27227f8c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27227f8c00 p_off=75467776 size=131072 end_off=75598848 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f2721995c00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721995c00 p_off=60382208 size=131072 end_off=60513280 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e3c0000 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e3c0000 p_off=3932160 size=131072 end_off=4063232 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721df5c00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721df5c00 p_off=64969728 size=131072 end_off=65100800 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722818c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722818c00 p_off=75598848 size=131072 end_off=75729920 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f27219b5c00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27219b5c00 p_off=60513280 size=131072 end_off=60644352 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721e15c00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721e15c00 p_off=65100800 size=131072 end_off=65231872 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e3e0000 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e3e0000 p_off=4063232 size=131072 end_off=4194304 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722838c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722838c00 p_off=75729920 size=131072 end_off=75860992 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f27219d5c00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27219d5c00 p_off=60644352 size=131072 end_off=60775424 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e400000 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e400000 p_off=4194304 size=131072 end_off=4325376 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722858c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722858c00 p_off=75860992 size=131072 end_off=75992064 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f27223f8c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27223f8c00 p_off=71273472 size=131072 end_off=71404544 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721e35c00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721e35c00 p_off=65231872 size=131072 end_off=65362944 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f27219f5c00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27219f5c00 p_off=60775424 size=131072 end_off=60906496 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e420000 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e420000 p_off=4325376 size=131072 end_off=4456448 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722878c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722878c00 p_off=75992064 size=131072 end_off=76123136 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f2722418c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722418c00 p_off=71404544 size=131072 end_off=71535616 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721e55c00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721e55c00 p_off=65362944 size=131072 end_off=65494016 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f2722018c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722018c00 p_off=67210240 size=131072 end_off=67341312 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e440000 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e440000 p_off=4456448 size=131072 end_off=4587520 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722898c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722898c00 p_off=76123136 size=131072 end_off=76254208 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f2722438c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722438c00 p_off=71535616 size=131072 end_off=71666688 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f2722038c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722038c00 p_off=67341312 size=131072 end_off=67472384 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f27228b8c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27228b8c00 p_off=76254208 size=131072 end_off=76385280 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e460000 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e460000 p_off=4587520 size=131072 end_off=4718592 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721e75c00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721e75c00 p_off=65494016 size=131072 end_off=65625088 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f2722058c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722058c00 p_off=67472384 size=131072 end_off=67603456 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f27228d8c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27228d8c00 p_off=76385280 size=131072 end_off=76516352 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e480000 off=4718592 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e480000 p_off=4718592 size=131072 end_off=4849664 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f2722078c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722078c00 p_off=67603456 size=131072 end_off=67734528 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d990 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2721a35c00 dst1=0x7f2721e95c00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721e95c00 p_off=65625088 size=131072 end_off=65756160 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d820 buffer=0x7f27b94d3ab0 data(host)=0xc00074e000 dst0=0x7f27215b5c00 dst1=0x7f2721a15c00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2721a15c00 p_off=60906496 size=131072 end_off=61037568 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f27228f8c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27228f8c00 p_off=76516352 size=131072 end_off=76647424 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e4a0000 off=4849664 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f2722458c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722458c00 p_off=71666688 size=131072 end_off=71797760 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722918c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722918c00 p_off=76647424 size=131072 end_off=76778496 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f2722478c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722478c00 p_off=71797760 size=131072 end_off=71928832 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722938c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722938c00 p_off=76778496 size=131072 end_off=76909568 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f2722498c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722498c00 p_off=71928832 size=131072 end_off=72059904 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722c38c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722c38c00 p_off=79924224 size=131072 end_off=80055296 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f2722098c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722098c00 p_off=67734528 size=131072 end_off=67865600 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e7f0 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f27230b8c00 dst1=0x7f27230b8c00 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27230b8c00 p_off=84642816 size=3072 end_off=84645888 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e4a0000 p_off=4849664 size=131072 end_off=4980736 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e960 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f27230b9800 dst1=0x7f27230b9800 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27230b9800 p_off=84645888 size=3072 end_off=84648960 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722958c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722958c00 p_off=76909568 size=131072 end_off=77040640 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722c58c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722c58c00 p_off=80055296 size=131072 end_off=80186368 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800ead0 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f27230ba400 dst1=0x7f27230ba400 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27230ba400 p_off=84648960 size=3072 end_off=84652032 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722978c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e4c0000 off=4980736 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e4c0000 p_off=4980736 size=131072 end_off=5111808 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722978c00 p_off=77040640 size=131072 end_off=77171712 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f27224b8c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27224b8c00 p_off=72059904 size=131072 end_off=72190976 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f27220b8c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27220b8c00 p_off=67865600 size=131072 end_off=67996672 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f27224d8c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27224d8c00 p_off=72190976 size=131072 end_off=72322048 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722998c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722998c00 p_off=77171712 size=131072 end_off=77302784 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f27220d8c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27220d8c00 p_off=67996672 size=131072 end_off=68127744 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e4e0000 off=5111808 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e4e0000 p_off=5111808 size=131072 end_off=5242880 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f27224f8c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27224f8c00 p_off=72322048 size=131072 end_off=72453120 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f27229b8c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27229b8c00 p_off=77302784 size=131072 end_off=77433856 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f27220f8c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27220f8c00 p_off=68127744 size=131072 end_off=68258816 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e500000 off=5242880 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e500000 p_off=5242880 size=131072 end_off=5373952 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f2722518c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722518c00 p_off=72453120 size=131072 end_off=72584192 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f27229d8c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27229d8c00 p_off=77433856 size=131072 end_off=77564928 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f2722118c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722118c00 p_off=68258816 size=131072 end_off=68389888 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800ec40 buffer=0x7f27b94d3ab0 data(host)=0xc0008ca000 dst0=0x7f27230bb000 dst1=0x7f27230bb000 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27230bb000 p_off=84652032 size=3072 end_off=84655104 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f2722538c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722538c00 p_off=72584192 size=131072 end_off=72715264 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e520000 off=5373952 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e520000 p_off=5373952 size=131072 end_off=5505024 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f27229f8c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27229f8c00 p_off=77564928 size=131072 end_off=77696000 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722c78c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722c78c00 p_off=80186368 size=131072 end_off=80317440 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f27230bbc00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27230bbc00 p_off=84655104 size=131072 end_off=84786176 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f2722558c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722558c00 p_off=72715264 size=131072 end_off=72846336 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722a18c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722a18c00 p_off=77696000 size=131072 end_off=77827072 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e540000 off=5505024 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e540000 p_off=5505024 size=131072 end_off=5636096 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722c98c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f27230dbc00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27230dbc00 p_off=84786176 size=131072 end_off=84917248 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722c98c00 p_off=80317440 size=131072 end_off=80448512 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f2722578c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722578c00 p_off=72846336 size=131072 end_off=72977408 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722a38c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722a38c00 p_off=77827072 size=131072 end_off=77958144 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e560000 off=5636096 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e560000 p_off=5636096 size=131072 end_off=5767168 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f27230fbc00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27230fbc00 p_off=84917248 size=131072 end_off=85048320 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722cb8c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722cb8c00 p_off=80448512 size=131072 end_off=80579584 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722a58c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722a58c00 p_off=77958144 size=131072 end_off=78089216 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f2722598c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722598c00 p_off=72977408 size=131072 end_off=73108480 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f2722138c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722138c00 p_off=68389888 size=131072 end_off=68520960 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f272311bc00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272311bc00 p_off=85048320 size=131072 end_off=85179392 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722cd8c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f2722158c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722158c00 p_off=68520960 size=131072 end_off=68652032 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722cd8c00 p_off=80579584 size=131072 end_off=80710656 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f272313bc00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272313bc00 p_off=85179392 size=131072 end_off=85310464 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f2722178c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722178c00 p_off=68652032 size=131072 end_off=68783104 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f272315bc00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272315bc00 p_off=85310464 size=131072 end_off=85441536 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f27225b8c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27225b8c00 p_off=73108480 size=131072 end_off=73239552 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f272317bc00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272317bc00 p_off=85441536 size=131072 end_off=85572608 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f27225d8c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27225d8c00 p_off=73239552 size=131072 end_off=73370624 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e580000 off=5767168 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e580000 p_off=5767168 size=131072 end_off=5898240 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722cf8c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722cf8c00 p_off=80710656 size=131072 end_off=80841728 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f272319bc00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272319bc00 p_off=85572608 size=131072 end_off=85703680 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f27225f8c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27225f8c00 p_off=73370624 size=131072 end_off=73501696 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f2722198c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722198c00 p_off=68783104 size=131072 end_off=68914176 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e5a0000 off=5898240 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722d18c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722d18c00 p_off=80841728 size=131072 end_off=80972800 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e5a0000 p_off=5898240 size=131072 end_off=6029312 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f27231bbc00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27231bbc00 p_off=85703680 size=131072 end_off=85834752 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f2722618c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722618c00 p_off=73501696 size=131072 end_off=73632768 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f27221b8c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27221b8c00 p_off=68914176 size=131072 end_off=69045248 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722d38c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722d38c00 p_off=80972800 size=131072 end_off=81103872 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e5c0000 off=6029312 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e5c0000 p_off=6029312 size=131072 end_off=6160384 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f27231dbc00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27231dbc00 p_off=85834752 size=131072 end_off=85965824 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722a78c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722a78c00 p_off=78089216 size=131072 end_off=78220288 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f2722638c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e5e0000 off=6160384 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e5e0000 p_off=6160384 size=131072 end_off=6291456 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722638c00 p_off=73632768 size=131072 end_off=73763840 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f27231fbc00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27231fbc00 p_off=85965824 size=131072 end_off=86096896 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f27221d8c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27221d8c00 p_off=69045248 size=131072 end_off=69176320 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e600000 off=6291456 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e600000 p_off=6291456 size=131072 end_off=6422528 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722a98c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722a98c00 p_off=78220288 size=131072 end_off=78351360 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f2722658c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722658c00 p_off=73763840 size=131072 end_off=73894912 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f272321bc00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272321bc00 p_off=86096896 size=131072 end_off=86227968 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722d58c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722d58c00 p_off=81103872 size=131072 end_off=81234944 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722ab8c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722ab8c00 p_off=78351360 size=131072 end_off=78482432 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e0c0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f2721eb8c00 dst1=0x7f27221f8c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27221f8c00 p_off=69176320 size=131072 end_off=69307392 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e620000 off=6422528 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e620000 p_off=6422528 size=131072 end_off=6553600 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f272323bc00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272323bc00 p_off=86227968 size=131072 end_off=86359040 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722ad8c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722ad8c00 p_off=78482432 size=131072 end_off=78613504 OOB=0
[GGML-CUDA-DIAG] cuCtxGetCurrent BAD cr=0 CUDA_SUCCESS no error ctx=(nil)
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722d78c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] cuMemGetAddressRange FAILED cr=201 CUDA_ERROR_INVALID_CONTEXT invalid device context p=0x7f2722d78c00
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f2722678c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722678c00 p_off=73894912 size=131072 end_off=74025984 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800ef20 buffer=0x7f27b94d3ab0 data(host)=0xc00090a000 dst0=0x7f272341bc00 dst1=0x7f272341bc00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272341bc00 p_off=88194048 size=131072 end_off=88325120 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722af8c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722af8c00 p_off=78613504 size=131072 end_off=78744576 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722d98c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722d98c00 p_off=81366016 size=131072 end_off=81497088 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f2722698c00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722698c00 p_off=74025984 size=131072 end_off=74157056 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e640000 off=6553600 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722b18c00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722b18c00 p_off=78744576 size=131072 end_off=78875648 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e640000 p_off=6553600 size=131072 end_off=6684672 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f272325bc00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272325bc00 p_off=86359040 size=131072 end_off=86490112 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722db8c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722db8c00 p_off=81497088 size=131072 end_off=81628160 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f27226b8c00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27226b8c00 p_off=74157056 size=131072 end_off=74288128 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800ef20 buffer=0x7f27b94d3ab0 data(host)=0xc00090a000 dst0=0x7f272341bc00 dst1=0x7f272343bc00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272343bc00 p_off=88325120 size=131072 end_off=88456192 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722b38c00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722b38c00 p_off=78875648 size=131072 end_off=79006720 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722dd8c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722dd8c00 p_off=81628160 size=131072 end_off=81759232 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f272327bc00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272327bc00 p_off=86490112 size=131072 end_off=86621184 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f27226d8c00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27226d8c00 p_off=74288128 size=131072 end_off=74419200 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e660000 off=6684672 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e660000 p_off=6684672 size=131072 end_off=6815744 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800ef20 buffer=0x7f27b94d3ab0 data(host)=0xc00090a000 dst0=0x7f272341bc00 dst1=0x7f272345bc00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272345bc00 p_off=88456192 size=131072 end_off=88587264 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722b58c00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722b58c00 p_off=79006720 size=131072 end_off=79137792 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f27226f8c00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27226f8c00 p_off=74419200 size=131072 end_off=74550272 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f272329bc00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272329bc00 p_off=86621184 size=131072 end_off=86752256 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e680000 off=6815744 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e680000 p_off=6815744 size=131072 end_off=6946816 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800ef20 buffer=0x7f27b94d3ab0 data(host)=0xc00090a000 dst0=0x7f272341bc00 dst1=0x7f272347bc00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272347bc00 p_off=88587264 size=131072 end_off=88718336 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722b78c00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722b78c00 p_off=79137792 size=131072 end_off=79268864 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722b98c00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722b98c00 p_off=79268864 size=131072 end_off=79399936 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e6a0000 off=6946816 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e6a0000 p_off=6946816 size=131072 end_off=7077888 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f27232bbc00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27232bbc00 p_off=86752256 size=131072 end_off=86883328 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800ef20 buffer=0x7f27b94d3ab0 data(host)=0xc00090a000 dst0=0x7f272341bc00 dst1=0x7f272349bc00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272349bc00 p_off=88718336 size=131072 end_off=88849408 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722df8c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722df8c00 p_off=81759232 size=131072 end_off=81890304 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722bb8c00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722bb8c00 p_off=79399936 size=131072 end_off=79531008 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e6c0000 off=7077888 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e6c0000 p_off=7077888 size=131072 end_off=7208960 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800ef20 buffer=0x7f27b94d3ab0 data(host)=0xc00090a000 dst0=0x7f272341bc00 dst1=0x7f27234bbc00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27234bbc00 p_off=88849408 size=131072 end_off=88980480 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f27232dbc00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27232dbc00 p_off=86883328 size=131072 end_off=87014400 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722e18c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722e18c00 p_off=81890304 size=131072 end_off=82021376 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722bd8c00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722bd8c00 p_off=79531008 size=131072 end_off=79662080 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f2722718c00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722718c00 p_off=74550272 size=131072 end_off=74681344 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f27232fbc00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27232fbc00 p_off=87014400 size=131072 end_off=87145472 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722e38c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722e38c00 p_off=82021376 size=131072 end_off=82152448 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722bf8c00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722bf8c00 p_off=79662080 size=131072 end_off=79793152 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e6e0000 off=7208960 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e6e0000 p_off=7208960 size=131072 end_off=7340032 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f272331bc00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722e58c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722e58c00 p_off=82152448 size=131072 end_off=82283520 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e510 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f27227b8c00 dst1=0x7f2722c18c00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722c18c00 p_off=79793152 size=131072 end_off=79924224 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f2722738c00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722738c00 p_off=74681344 size=131072 end_off=74812416 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800ef20 buffer=0x7f27b94d3ab0 data(host)=0xc00090a000 dst0=0x7f272341bc00 dst1=0x7f27234dbc00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27234dbc00 p_off=88980480 size=131072 end_off=89111552 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e700000 off=7340032 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e700000 p_off=7340032 size=131072 end_off=7471104 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722e78c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722e78c00 p_off=82283520 size=131072 end_off=82414592 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f2722758c00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722758c00 p_off=74812416 size=131072 end_off=74943488 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722e98c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f272353bc00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800ef20 buffer=0x7f27b94d3ab0 data(host)=0xc00090a000 dst0=0x7f272341bc00 dst1=0x7f27234fbc00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272353bc00 p_off=89373696 size=131072 end_off=89504768 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27234fbc00 p_off=89111552 size=131072 end_off=89242624 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722e98c00 p_off=82414592 size=131072 end_off=82545664 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e720000 off=7471104 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e720000 p_off=7471104 size=131072 end_off=7602176 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f2722778c00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722778c00 p_off=74943488 size=131072 end_off=75074560 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272331bc00 p_off=87145472 size=131072 end_off=87276544 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800ef20 buffer=0x7f27b94d3ab0 data(host)=0xc00090a000 dst0=0x7f272341bc00 dst1=0x7f272351bc00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f272355bc00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272355bc00 p_off=89504768 size=131072 end_off=89635840 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272351bc00 p_off=89242624 size=131072 end_off=89373696 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e740000 off=7602176 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e740000 p_off=7602176 size=131072 end_off=7733248 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f272333bc00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272333bc00 p_off=87276544 size=131072 end_off=87407616 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f272357bc00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272357bc00 p_off=89635840 size=131072 end_off=89766912 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722eb8c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722eb8c00 p_off=82545664 size=131072 end_off=82676736 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f272359bc00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272359bc00 p_off=89766912 size=131072 end_off=89897984 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f27239bbc00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27239bbc00 p_off=94092288 size=131072 end_off=94223360 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722ed8c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722ed8c00 p_off=82676736 size=131072 end_off=82807808 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e760000 off=7733248 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e760000 p_off=7733248 size=131072 end_off=7864320 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e3a0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2722338c00 dst1=0x7f2722798c00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722798c00 p_off=75074560 size=131072 end_off=75205632 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f27235bbc00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27235bbc00 p_off=89897984 size=131072 end_off=90029056 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f27239dbc00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27239dbc00 p_off=94223360 size=131072 end_off=94354432 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722ef8c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722ef8c00 p_off=82807808 size=131072 end_off=82938880 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f27239fbc00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27239fbc00 p_off=94354432 size=131072 end_off=94485504 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722f18c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722f18c00 p_off=82938880 size=131072 end_off=83069952 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f2723e3bc00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723e3bc00 p_off=98810880 size=131072 end_off=98941952 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f27235dbc00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27235dbc00 p_off=90029056 size=131072 end_off=90160128 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723a1bc00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723a1bc00 p_off=94485504 size=131072 end_off=94616576 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722f38c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722f38c00 p_off=83069952 size=131072 end_off=83201024 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f2723e5bc00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723e5bc00 p_off=98941952 size=131072 end_off=99073024 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f2723e7bc00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723e7bc00 p_off=99073024 size=131072 end_off=99204096 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722f58c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722f58c00 p_off=83201024 size=131072 end_off=83332096 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723a3bc00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723a3bc00 p_off=94616576 size=131072 end_off=94747648 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f27235fbc00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27235fbc00 p_off=90160128 size=131072 end_off=90291200 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f272335bc00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272335bc00 p_off=87407616 size=131072 end_off=87538688 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e780000 off=7864320 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e780000 p_off=7864320 size=131072 end_off=7995392 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722f78c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722f78c00 p_off=83332096 size=131072 end_off=83463168 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723a5bc00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723a5bc00 p_off=94747648 size=131072 end_off=94878720 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f2723e9bc00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723e9bc00 p_off=99204096 size=131072 end_off=99335168 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f272361bc00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272361bc00 p_off=90291200 size=131072 end_off=90422272 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e7a0000 off=7995392 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e7a0000 p_off=7995392 size=131072 end_off=8126464 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f272337bc00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272337bc00 p_off=87538688 size=131072 end_off=87669760 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722f98c00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723a7bc00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723a7bc00 p_off=94878720 size=131072 end_off=95009792 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722f98c00 p_off=83463168 size=131072 end_off=83594240 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f272363bc00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272363bc00 p_off=90422272 size=131072 end_off=90553344 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e7c0000 off=8126464 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e7c0000 p_off=8126464 size=131072 end_off=8257536 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f272339bc00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272339bc00 p_off=87669760 size=131072 end_off=87800832 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723a9bc00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723a9bc00 p_off=95009792 size=131072 end_off=95140864 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f272365bc00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272365bc00 p_off=90553344 size=131072 end_off=90684416 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e7e0000 off=8257536 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e7e0000 p_off=8257536 size=131072 end_off=8388608 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722fb8c00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722fb8c00 p_off=83594240 size=131072 end_off=83725312 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f27233bbc00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27233bbc00 p_off=87800832 size=131072 end_off=87931904 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f2723ebbc00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723ebbc00 p_off=99335168 size=131072 end_off=99466240 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f272367bc00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272367bc00 p_off=90684416 size=131072 end_off=90815488 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e800000 off=8388608 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e800000 p_off=8388608 size=131072 end_off=8519680 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722fd8c00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722fd8c00 p_off=83725312 size=131072 end_off=83856384 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f2723edbc00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723edbc00 p_off=99466240 size=131072 end_off=99597312 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f27233dbc00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27233dbc00 p_off=87931904 size=131072 end_off=88062976 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f272369bc00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272369bc00 p_off=90815488 size=131072 end_off=90946560 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2722ff8c00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2722ff8c00 p_off=83856384 size=131072 end_off=83987456 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f2723efbc00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723efbc00 p_off=99597312 size=131072 end_off=99728384 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723abbc00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723abbc00 p_off=95140864 size=131072 end_off=95271936 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800edb0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27230bbc00 dst1=0x7f27233fbc00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27233fbc00 p_off=88062976 size=131072 end_off=88194048 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e820000 off=8519680 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e820000 p_off=8519680 size=131072 end_off=8650752 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f27236bbc00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27236bbc00 p_off=90946560 size=131072 end_off=91077632 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2723018c00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723018c00 p_off=83987456 size=131072 end_off=84118528 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723adbc00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723adbc00 p_off=95271936 size=131072 end_off=95403008 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f4e0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27242bbc00 dst1=0x7f27242bbc00 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27242bbc00 p_off=103529472 size=3072 end_off=103532544 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e840000 off=8650752 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e840000 p_off=8650752 size=131072 end_off=8781824 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723afbc00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f27236dbc00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27236dbc00 p_off=91077632 size=131072 end_off=91208704 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723afbc00 p_off=95403008 size=131072 end_off=95534080 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f650 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f27242bc800 dst1=0x7f27242bc800 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27242bc800 p_off=103532544 size=3072 end_off=103535616 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f7c0 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f27242bd400 dst1=0x7f27242bd400 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27242bd400 p_off=103535616 size=3072 end_off=103538688 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f930 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f27242be000 dst1=0x7f27242be000 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27242be000 p_off=103538688 size=3072 end_off=103541760 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f27236fbc00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27236fbc00 p_off=91208704 size=131072 end_off=91339776 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2723038c00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723038c00 p_off=84118528 size=131072 end_off=84249600 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f2723f1bc00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723f1bc00 p_off=99728384 size=131072 end_off=99859456 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f272371bc00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272371bc00 p_off=91339776 size=131072 end_off=91470848 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f2723f3bc00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723f3bc00 p_off=99859456 size=131072 end_off=99990528 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f272373bc00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272373bc00 p_off=91470848 size=131072 end_off=91601920 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f2723f5bc00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723f5bc00 p_off=99990528 size=131072 end_off=100121600 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2723058c00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723058c00 p_off=84249600 size=131072 end_off=84380672 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723b1bc00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723b1bc00 p_off=95534080 size=131072 end_off=95665152 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e860000 off=8781824 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e860000 p_off=8781824 size=131072 end_off=8912896 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f2723f7bc00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723f7bc00 p_off=100121600 size=131072 end_off=100252672 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f27242bec00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27242bec00 p_off=103541760 size=131072 end_off=103672832 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2723078c00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723078c00 p_off=84380672 size=131072 end_off=84511744 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723b3bc00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723b3bc00 p_off=95665152 size=131072 end_off=95796224 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800e680 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2722c38c00 dst1=0x7f2723098c00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723098c00 p_off=84511744 size=131072 end_off=84642816 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f2723f9bc00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723f9bc00 p_off=100252672 size=131072 end_off=100383744 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f272375bc00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272375bc00 p_off=91601920 size=131072 end_off=91732992 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e880000 off=8912896 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e880000 p_off=8912896 size=131072 end_off=9043968 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f27242dec00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27242dec00 p_off=103672832 size=131072 end_off=103803904 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723b5bc00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723b5bc00 p_off=95796224 size=131072 end_off=95927296 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f272377bc00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272377bc00 p_off=91732992 size=131072 end_off=91864064 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723b7bc00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723b7bc00 p_off=95927296 size=131072 end_off=96058368 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fc10 buffer=0x7f27b94d3ab0 data(host)=0xc000a2a000 dst0=0x7f272461ec00 dst1=0x7f272461ec00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272461ec00 p_off=107080704 size=131072 end_off=107211776 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e8a0000 off=9043968 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e8a0000 p_off=9043968 size=131072 end_off=9175040 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f2723fbbc00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723fbbc00 p_off=100383744 size=131072 end_off=100514816 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723b9bc00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723b9bc00 p_off=96058368 size=131072 end_off=96189440 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fc10 buffer=0x7f27b94d3ab0 data(host)=0xc000a2a000 dst0=0x7f272461ec00 dst1=0x7f272463ec00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272463ec00 p_off=107211776 size=131072 end_off=107342848 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f27242fec00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27242fec00 p_off=103803904 size=131072 end_off=103934976 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e8c0000 off=9175040 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e8c0000 p_off=9175040 size=131072 end_off=9306112 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723bbbc00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723bbbc00 p_off=96189440 size=131072 end_off=96320512 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f272431ec00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272431ec00 p_off=103934976 size=131072 end_off=104066048 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f2723fdbc00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fc10 buffer=0x7f27b94d3ab0 data(host)=0xc000a2a000 dst0=0x7f272461ec00 dst1=0x7f272465ec00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272465ec00 p_off=107342848 size=131072 end_off=107473920 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723fdbc00 p_off=100514816 size=131072 end_off=100645888 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f272379bc00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272379bc00 p_off=91864064 size=131072 end_off=91995136 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723bdbc00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723bdbc00 p_off=96320512 size=131072 end_off=96451584 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f272433ec00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272433ec00 p_off=104066048 size=131072 end_off=104197120 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f2723ffbc00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fc10 buffer=0x7f27b94d3ab0 data(host)=0xc000a2a000 dst0=0x7f272461ec00 dst1=0x7f272467ec00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272467ec00 p_off=107473920 size=131072 end_off=107604992 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723ffbc00 p_off=100645888 size=131072 end_off=100776960 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f27237bbc00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27237bbc00 p_off=91995136 size=131072 end_off=92126208 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723bfbc00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723bfbc00 p_off=96451584 size=131072 end_off=96582656 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f272435ec00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272435ec00 p_off=104197120 size=131072 end_off=104328192 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f27237dbc00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27237dbc00 p_off=92126208 size=131072 end_off=92257280 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f272401bc00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272401bc00 p_off=100776960 size=131072 end_off=100908032 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fc10 buffer=0x7f27b94d3ab0 data(host)=0xc000a2a000 dst0=0x7f272461ec00 dst1=0x7f272469ec00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272469ec00 p_off=107604992 size=131072 end_off=107736064 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723c1bc00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723c1bc00 p_off=96582656 size=131072 end_off=96713728 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f27237fbc00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27237fbc00 p_off=92257280 size=131072 end_off=92388352 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e8e0000 off=9306112 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e8e0000 p_off=9306112 size=131072 end_off=9437184 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f272437ec00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272437ec00 p_off=104328192 size=131072 end_off=104459264 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f272403bc00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272403bc00 p_off=100908032 size=131072 end_off=101039104 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723c3bc00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723c3bc00 p_off=96713728 size=131072 end_off=96844800 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e900000 off=9437184 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e900000 p_off=9437184 size=131072 end_off=9568256 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f272439ec00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272439ec00 p_off=104459264 size=131072 end_off=104590336 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fc10 buffer=0x7f27b94d3ab0 data(host)=0xc000a2a000 dst0=0x7f272461ec00 dst1=0x7f27246bec00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27246bec00 p_off=107736064 size=131072 end_off=107867136 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723c5bc00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723c5bc00 p_off=96844800 size=131072 end_off=96975872 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f27243bec00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27243bec00 p_off=104590336 size=131072 end_off=104721408 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fc10 buffer=0x7f27b94d3ab0 data(host)=0xc000a2a000 dst0=0x7f272461ec00 dst1=0x7f27246dec00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27246dec00 p_off=107867136 size=131072 end_off=107998208 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f272381bc00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272381bc00 p_off=92388352 size=131072 end_off=92519424 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e920000 off=9568256 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e920000 p_off=9568256 size=131072 end_off=9699328 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723c7bc00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723c7bc00 p_off=96975872 size=131072 end_off=97106944 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f27243dec00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27243dec00 p_off=104721408 size=131072 end_off=104852480 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f272405bc00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272405bc00 p_off=101039104 size=131072 end_off=101170176 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fc10 buffer=0x7f27b94d3ab0 data(host)=0xc000a2a000 dst0=0x7f272461ec00 dst1=0x7f27246fec00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27246fec00 p_off=107998208 size=131072 end_off=108129280 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723c9bc00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723c9bc00 p_off=97106944 size=131072 end_off=97238016 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f272383bc00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e940000 off=9699328 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e940000 p_off=9699328 size=131072 end_off=9830400 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f27243fec00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27243fec00 p_off=104852480 size=131072 end_off=104983552 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f272407bc00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272407bc00 p_off=101170176 size=131072 end_off=101301248 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272383bc00 p_off=92519424 size=131072 end_off=92650496 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f272441ec00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272441ec00 p_off=104983552 size=131072 end_off=105114624 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723cbbc00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723cbbc00 p_off=97238016 size=131072 end_off=97369088 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e960000 off=9830400 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e960000 p_off=9830400 size=131072 end_off=9961472 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fc10 buffer=0x7f27b94d3ab0 data(host)=0xc000a2a000 dst0=0x7f272461ec00 dst1=0x7f272471ec00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272471ec00 p_off=108129280 size=131072 end_off=108260352 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f272409bc00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272409bc00 p_off=101301248 size=131072 end_off=101432320 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f272385bc00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272385bc00 p_off=92650496 size=131072 end_off=92781568 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f272443ec00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272443ec00 p_off=105114624 size=131072 end_off=105245696 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723cdbc00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723cdbc00 p_off=97369088 size=131072 end_off=97500160 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f272445ec00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272445ec00 p_off=105245696 size=131072 end_off=105376768 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723cfbc00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723cfbc00 p_off=97500160 size=131072 end_off=97631232 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f272447ec00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272447ec00 p_off=105376768 size=131072 end_off=105507840 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723d1bc00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723d1bc00 p_off=97631232 size=131072 end_off=97762304 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f272473ec00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272473ec00 p_off=108260352 size=131072 end_off=108391424 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f27240bbc00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27240bbc00 p_off=101432320 size=131072 end_off=101563392 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f272449ec00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272449ec00 p_off=105507840 size=131072 end_off=105638912 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723d3bc00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723d3bc00 p_off=97762304 size=131072 end_off=97893376 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f27240dbc00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27240dbc00 p_off=101563392 size=131072 end_off=101694464 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f27244bec00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27244bec00 p_off=105638912 size=131072 end_off=105769984 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f272387bc00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272387bc00 p_off=92781568 size=131072 end_off=92912640 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e980000 off=9961472 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e980000 p_off=9961472 size=131072 end_off=10092544 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723d5bc00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723d5bc00 p_off=97893376 size=131072 end_off=98024448 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f27240fbc00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27240fbc00 p_off=101694464 size=131072 end_off=101825536 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f27244dec00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27244dec00 p_off=105769984 size=131072 end_off=105901056 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f272389bc00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272389bc00 p_off=92912640 size=131072 end_off=93043712 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723d7bc00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723d7bc00 p_off=98024448 size=131072 end_off=98155520 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f272411bc00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272411bc00 p_off=101825536 size=131072 end_off=101956608 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f272475ec00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272475ec00 p_off=108391424 size=131072 end_off=108522496 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f27238bbc00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27238bbc00 p_off=93043712 size=131072 end_off=93174784 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723d9bc00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723d9bc00 p_off=98155520 size=131072 end_off=98286592 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f272413bc00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272413bc00 p_off=101956608 size=131072 end_off=102087680 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e9a0000 off=10092544 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e9a0000 p_off=10092544 size=131072 end_off=10223616 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f272477ec00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272477ec00 p_off=108522496 size=131072 end_off=108653568 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f27238dbc00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27238dbc00 p_off=93174784 size=131072 end_off=93305856 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723dbbc00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723dbbc00 p_off=98286592 size=131072 end_off=98417664 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e9c0000 off=10223616 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e9c0000 p_off=10223616 size=131072 end_off=10354688 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f272415bc00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272415bc00 p_off=102087680 size=131072 end_off=102218752 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f27244fec00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27244fec00 p_off=105901056 size=131072 end_off=106032128 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723ddbc00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723ddbc00 p_off=98417664 size=131072 end_off=98548736 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f27238fbc00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27238fbc00 p_off=93305856 size=131072 end_off=93436928 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271e9e0000 off=10354688 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271e9e0000 p_off=10354688 size=131072 end_off=10485760 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f272479ec00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272479ec00 p_off=108653568 size=131072 end_off=108784640 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f272417bc00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272417bc00 p_off=102218752 size=131072 end_off=102349824 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f272451ec00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272451ec00 p_off=106032128 size=131072 end_off=106163200 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723dfbc00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723dfbc00 p_off=98548736 size=131072 end_off=98679808 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f272419bc00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272419bc00 p_off=102349824 size=131072 end_off=102480896 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f27247bec00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27247bec00 p_off=108784640 size=131072 end_off=108915712 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f200 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f27239bbc00 dst1=0x7f2723e1bc00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2723e1bc00 p_off=98679808 size=131072 end_off=98810880 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f272453ec00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272453ec00 p_off=106163200 size=131072 end_off=106294272 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ea00000 off=10485760 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ea00000 p_off=10485760 size=131072 end_off=10616832 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f27247dec00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27247dec00 p_off=108915712 size=131072 end_off=109046784 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f272391bc00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272391bc00 p_off=93436928 size=131072 end_off=93568000 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f27241bbc00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27241bbc00 p_off=102480896 size=131072 end_off=102611968 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f272455ec00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272455ec00 p_off=106294272 size=131072 end_off=106425344 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ea20000 off=10616832 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ea20000 p_off=10616832 size=131072 end_off=10747904 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f27241dbc00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27241dbc00 p_off=102611968 size=131072 end_off=102743040 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f27247fec00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27247fec00 p_off=109046784 size=131072 end_off=109177856 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f272457ec00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272457ec00 p_off=106425344 size=131072 end_off=106556416 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ea40000 off=10747904 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ea40000 p_off=10747904 size=131072 end_off=10878976 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f27241fbc00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27241fbc00 p_off=102743040 size=131072 end_off=102874112 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f272459ec00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272459ec00 p_off=106556416 size=131072 end_off=106687488 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f27245bec00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27245bec00 p_off=106687488 size=131072 end_off=106818560 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ea60000 off=10878976 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ea60000 p_off=10878976 size=131072 end_off=11010048 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f272393bc00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272393bc00 p_off=93568000 size=131072 end_off=93699072 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ea80000 off=11010048 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ea80000 p_off=11010048 size=131072 end_off=11141120 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f272395bc00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272395bc00 p_off=93699072 size=131072 end_off=93830144 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724bbec00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724bbec00 p_off=112978944 size=131072 end_off=113110016 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271eaa0000 off=11141120 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271eaa0000 p_off=11141120 size=131072 end_off=11272192 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f272397bc00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272397bc00 p_off=93830144 size=131072 end_off=93961216 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724bdec00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724bdec00 p_off=113110016 size=131072 end_off=113241088 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271eac0000 off=11272192 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271eac0000 p_off=11272192 size=131072 end_off=11403264 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f090 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272353bc00 dst1=0x7f272399bc00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272399bc00 p_off=93961216 size=131072 end_off=94092288 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724bfec00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724bfec00 p_off=113241088 size=131072 end_off=113372160 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271eae0000 off=11403264 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271eae0000 p_off=11403264 size=131072 end_off=11534336 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f27245dec00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f272421bc00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272421bc00 p_off=102874112 size=131072 end_off=103005184 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27245dec00 p_off=106818560 size=131072 end_off=106949632 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271eb00000 off=11534336 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271eb00000 p_off=11534336 size=131072 end_off=11665408 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800faa0 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f27242bec00 dst1=0x7f27245fec00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27245fec00 p_off=106949632 size=131072 end_off=107080704 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f272423bc00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272423bc00 p_off=103005184 size=131072 end_off=103136256 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f272481ec00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272481ec00 p_off=109177856 size=131072 end_off=109308928 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271eb20000 off=11665408 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271eb20000 p_off=11665408 size=131072 end_off=11796480 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80101d0 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f27254bec00 dst1=0x7f27254bec00 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27254bec00 p_off=122416128 size=3072 end_off=122419200 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f272503ec00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272503ec00 p_off=117697536 size=131072 end_off=117828608 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010340 buffer=0x7f27b94d3ab0 data(host)=0xc000aca000 dst0=0x7f27254bf800 dst1=0x7f27254bf800 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27254bf800 p_off=122419200 size=3072 end_off=122422272 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f272483ec00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272483ec00 p_off=109308928 size=131072 end_off=109440000 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f272425bc00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272425bc00 p_off=103136256 size=131072 end_off=103267328 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271eb40000 off=11796480 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271eb40000 p_off=11796480 size=131072 end_off=11927552 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f272485ec00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272485ec00 p_off=109440000 size=131072 end_off=109571072 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271eb60000 off=11927552 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271eb60000 p_off=11927552 size=131072 end_off=12058624 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f272487ec00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272487ec00 p_off=109571072 size=131072 end_off=109702144 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f272489ec00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272489ec00 p_off=109702144 size=131072 end_off=109833216 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724c1ec00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724c1ec00 p_off=113372160 size=131072 end_off=113503232 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f27248bec00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27248bec00 p_off=109833216 size=131072 end_off=109964288 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80104b0 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f27254c0400 dst1=0x7f27254c0400 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27254c0400 p_off=122422272 size=3072 end_off=122425344 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724c3ec00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724c3ec00 p_off=113503232 size=131072 end_off=113634304 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010620 buffer=0x7f27b94d3ab0 data(host)=0xc000b0a000 dst0=0x7f27254c1000 dst1=0x7f27254c1000 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27254c1000 p_off=122425344 size=3072 end_off=122428416 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724c5ec00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724c5ec00 p_off=113634304 size=131072 end_off=113765376 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f272505ec00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272505ec00 p_off=117828608 size=131072 end_off=117959680 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271eb80000 off=12058624 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271eb80000 p_off=12058624 size=131072 end_off=12189696 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724c7ec00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724c7ec00 p_off=113765376 size=131072 end_off=113896448 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f27254c1c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27254c1c00 p_off=122428416 size=131072 end_off=122559488 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f272427bc00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272427bc00 p_off=103267328 size=131072 end_off=103398400 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f272507ec00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271eba0000 off=12189696 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f27248dec00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27248dec00 p_off=109964288 size=131072 end_off=110095360 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271eba0000 p_off=12189696 size=131072 end_off=12320768 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272507ec00 p_off=117959680 size=131072 end_off=118090752 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800f370 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f2723e3bc00 dst1=0x7f272429bc00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272429bc00 p_off=103398400 size=131072 end_off=103529472 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f27254e1c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27254e1c00 p_off=122559488 size=131072 end_off=122690560 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ebc0000 off=12320768 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ebc0000 p_off=12320768 size=131072 end_off=12451840 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f272509ec00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272509ec00 p_off=118090752 size=131072 end_off=118221824 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f2725501c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725501c00 p_off=122690560 size=131072 end_off=122821632 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ebe0000 off=12451840 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ebe0000 p_off=12451840 size=131072 end_off=12582912 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f27250bec00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010900 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f2725821c00 dst1=0x7f2725821c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725821c00 p_off=125967360 size=131072 end_off=126098432 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f2725521c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725521c00 p_off=122821632 size=131072 end_off=122952704 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f27248fec00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ec00000 off=12582912 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27250bec00 p_off=118221824 size=131072 end_off=118352896 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27248fec00 p_off=110095360 size=131072 end_off=110226432 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ec00000 p_off=12582912 size=131072 end_off=12713984 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010900 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f2725821c00 dst1=0x7f2725841c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725841c00 p_off=126098432 size=131072 end_off=126229504 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f2725541c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725541c00 p_off=122952704 size=131072 end_off=123083776 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010900 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f2725821c00 dst1=0x7f2725861c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725861c00 p_off=126229504 size=131072 end_off=126360576 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ec20000 off=12713984 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ec20000 p_off=12713984 size=131072 end_off=12845056 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f272491ec00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272491ec00 p_off=110226432 size=131072 end_off=110357504 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f2725561c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725561c00 p_off=123083776 size=131072 end_off=123214848 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010900 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f2725821c00 dst1=0x7f2725881c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725881c00 p_off=126360576 size=131072 end_off=126491648 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724c9ec00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724c9ec00 p_off=113896448 size=131072 end_off=114027520 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f272493ec00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272493ec00 p_off=110357504 size=131072 end_off=110488576 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f2725581c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725581c00 p_off=123214848 size=131072 end_off=123345920 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ec40000 off=12845056 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ec40000 p_off=12845056 size=131072 end_off=12976128 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f27250dec00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27250dec00 p_off=118352896 size=131072 end_off=118483968 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724cbec00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724cbec00 p_off=114027520 size=131072 end_off=114158592 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f27255a1c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27255a1c00 p_off=123345920 size=131072 end_off=123476992 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ec60000 off=12976128 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ec60000 p_off=12976128 size=131072 end_off=13107200 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f27250fec00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27250fec00 p_off=118483968 size=131072 end_off=118615040 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724cdec00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724cdec00 p_off=114158592 size=131072 end_off=114289664 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f27255c1c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27255c1c00 p_off=123476992 size=131072 end_off=123608064 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ec80000 off=13107200 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ec80000 p_off=13107200 size=131072 end_off=13238272 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f272495ec00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272495ec00 p_off=110488576 size=131072 end_off=110619648 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724cfec00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724cfec00 p_off=114289664 size=131072 end_off=114420736 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f27255e1c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27255e1c00 p_off=123608064 size=131072 end_off=123739136 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271eca0000 off=13238272 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271eca0000 p_off=13238272 size=131072 end_off=13369344 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f272511ec00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272511ec00 p_off=118615040 size=131072 end_off=118746112 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010900 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f2725821c00 dst1=0x7f27258a1c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27258a1c00 p_off=126491648 size=131072 end_off=126622720 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f2725601c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725601c00 p_off=123739136 size=131072 end_off=123870208 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f272513ec00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272513ec00 p_off=118746112 size=131072 end_off=118877184 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ecc0000 off=13369344 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ecc0000 p_off=13369344 size=131072 end_off=13500416 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f2725621c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725621c00 p_off=123870208 size=131072 end_off=124001280 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724d1ec00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724d1ec00 p_off=114420736 size=131072 end_off=114551808 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f272515ec00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272515ec00 p_off=118877184 size=131072 end_off=119008256 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010900 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f2725821c00 dst1=0x7f27258c1c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27258c1c00 p_off=126622720 size=131072 end_off=126753792 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ece0000 off=13500416 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ece0000 p_off=13500416 size=131072 end_off=13631488 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f2725641c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f272517ec00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272517ec00 p_off=119008256 size=131072 end_off=119139328 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ed00000 off=13631488 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ed00000 p_off=13631488 size=131072 end_off=13762560 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010900 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f2725821c00 dst1=0x7f27258e1c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27258e1c00 p_off=126753792 size=131072 end_off=126884864 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725641c00 p_off=124001280 size=131072 end_off=124132352 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010900 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f2725821c00 dst1=0x7f2725901c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725901c00 p_off=126884864 size=131072 end_off=127015936 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f272519ec00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272519ec00 p_off=119139328 size=131072 end_off=119270400 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f272497ec00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272497ec00 p_off=110619648 size=131072 end_off=110750720 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ed20000 off=13762560 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ed20000 p_off=13762560 size=131072 end_off=13893632 OOB=0
[GGML-CUDA-DIAG] cuCtxGetCurrent BAD cr=0 CUDA_SUCCESS no error ctx=(nil)
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724d3ec00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] cuMemGetAddressRange FAILED cr=201 CUDA_ERROR_INVALID_CONTEXT invalid device context p=0x7f2724d3ec00
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f2725661c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725661c00 p_off=124132352 size=131072 end_off=124263424 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f272499ec00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272499ec00 p_off=110750720 size=131072 end_off=110881792 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f2725681c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725681c00 p_off=124263424 size=131072 end_off=124394496 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010900 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f2725821c00 dst1=0x7f2725921c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725921c00 p_off=127015936 size=131072 end_off=127147008 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ed40000 off=13893632 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ed40000 p_off=13893632 size=131072 end_off=14024704 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f27251bec00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27251bec00 p_off=119270400 size=131072 end_off=119401472 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724d5ec00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724d5ec00 p_off=114682880 size=131072 end_off=114813952 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f27249bec00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27249bec00 p_off=110881792 size=131072 end_off=111012864 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f27251dec00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27251dec00 p_off=119401472 size=131072 end_off=119532544 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f27256a1c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27256a1c00 p_off=124394496 size=131072 end_off=124525568 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ed60000 off=14024704 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ed60000 p_off=14024704 size=131072 end_off=14155776 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724d7ec00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724d7ec00 p_off=114813952 size=131072 end_off=114945024 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f27249dec00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27249dec00 p_off=111012864 size=131072 end_off=111143936 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f27256c1c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27256c1c00 p_off=124525568 size=131072 end_off=124656640 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f27249fec00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27249fec00 p_off=111143936 size=131072 end_off=111275008 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f27251fec00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27251fec00 p_off=119532544 size=131072 end_off=119663616 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f2724a1ec00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724a1ec00 p_off=111275008 size=131072 end_off=111406080 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f272521ec00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272521ec00 p_off=119663616 size=131072 end_off=119794688 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f27256e1c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27256e1c00 p_off=124656640 size=131072 end_off=124787712 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f2724a3ec00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724a3ec00 p_off=111406080 size=131072 end_off=111537152 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724d9ec00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724d9ec00 p_off=114945024 size=131072 end_off=115076096 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725941c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725941c00 p_off=127147008 size=131072 end_off=127278080 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f272523ec00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272523ec00 p_off=119794688 size=131072 end_off=119925760 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ed80000 off=14155776 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ed80000 p_off=14155776 size=131072 end_off=14286848 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f2725701c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725701c00 p_off=124787712 size=131072 end_off=124918784 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f2724a5ec00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724a5ec00 p_off=111537152 size=131072 end_off=111668224 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271eda0000 off=14286848 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271eda0000 p_off=14286848 size=131072 end_off=14417920 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725961c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725961c00 p_off=127278080 size=131072 end_off=127409152 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f2725721c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725721c00 p_off=124918784 size=131072 end_off=125049856 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724dbec00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724dbec00 p_off=115076096 size=131072 end_off=115207168 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f2724a7ec00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724a7ec00 p_off=111668224 size=131072 end_off=111799296 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271edc0000 off=14417920 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271edc0000 p_off=14417920 size=131072 end_off=14548992 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f2725741c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725741c00 p_off=125049856 size=131072 end_off=125180928 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f272525ec00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272525ec00 p_off=119925760 size=131072 end_off=120056832 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f2724a9ec00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724a9ec00 p_off=111799296 size=131072 end_off=111930368 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ede0000 off=14548992 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ede0000 p_off=14548992 size=131072 end_off=14680064 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f272527ec00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272527ec00 p_off=120056832 size=131072 end_off=120187904 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724ddec00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724ddec00 p_off=115207168 size=131072 end_off=115338240 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f2725761c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725761c00 p_off=125180928 size=131072 end_off=125312000 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f2724abec00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724abec00 p_off=111930368 size=131072 end_off=112061440 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ee00000 off=14680064 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ee00000 p_off=14680064 size=131072 end_off=14811136 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724dfec00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724dfec00 p_off=115338240 size=131072 end_off=115469312 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725981c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725981c00 p_off=127409152 size=131072 end_off=127540224 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f2724adec00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724adec00 p_off=112061440 size=131072 end_off=112192512 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ee20000 off=14811136 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ee20000 p_off=14811136 size=131072 end_off=14942208 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724e1ec00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724e1ec00 p_off=115469312 size=131072 end_off=115600384 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f2725781c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725781c00 p_off=125312000 size=131072 end_off=125443072 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f272529ec00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272529ec00 p_off=120187904 size=131072 end_off=120318976 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724e3ec00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724e3ec00 p_off=115600384 size=131072 end_off=115731456 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f27257a1c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27257a1c00 p_off=125443072 size=131072 end_off=125574144 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f2724afec00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724afec00 p_off=112192512 size=131072 end_off=112323584 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ee40000 off=14942208 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ee40000 p_off=14942208 size=131072 end_off=15073280 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f27252bec00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27252bec00 p_off=120318976 size=131072 end_off=120450048 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f27257c1c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27257c1c00 p_off=125574144 size=131072 end_off=125705216 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f2724b1ec00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724b1ec00 p_off=112323584 size=131072 end_off=112454656 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f27252dec00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27252dec00 p_off=120450048 size=131072 end_off=120581120 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ee60000 off=15073280 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ee60000 p_off=15073280 size=131072 end_off=15204352 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724e5ec00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724e5ec00 p_off=115731456 size=131072 end_off=115862528 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f27257e1c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27257e1c00 p_off=125705216 size=131072 end_off=125836288 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f2724b3ec00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724b3ec00 p_off=112454656 size=131072 end_off=112585728 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f27252fec00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27252fec00 p_off=120581120 size=131072 end_off=120712192 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010790 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f27254c1c00 dst1=0x7f2725801c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725801c00 p_off=125836288 size=131072 end_off=125967360 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ee80000 off=15204352 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ee80000 p_off=15204352 size=131072 end_off=15335424 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f2724b5ec00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724b5ec00 p_off=112585728 size=131072 end_off=112716800 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f27259a1c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27259a1c00 p_off=127540224 size=131072 end_off=127671296 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724e7ec00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724e7ec00 p_off=115862528 size=131072 end_off=115993600 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271eea0000 off=15335424 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271eea0000 p_off=15335424 size=131072 end_off=15466496 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f2724b7ec00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724b7ec00 p_off=112716800 size=131072 end_off=112847872 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f27259c1c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27259c1c00 p_off=127671296 size=131072 end_off=127802368 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2725dc1c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725dc1c00 p_off=131865600 size=131072 end_off=131996672 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271eec0000 off=15466496 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f27259e1c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27259e1c00 p_off=127802368 size=131072 end_off=127933440 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271eec0000 p_off=15466496 size=131072 end_off=15597568 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fd80 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272473ec00 dst1=0x7f2724b9ec00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724b9ec00 p_off=112847872 size=131072 end_off=112978944 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724e9ec00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724e9ec00 p_off=115993600 size=131072 end_off=116124672 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2725de1c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725de1c00 p_off=131996672 size=131072 end_off=132127744 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725a01c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725a01c00 p_off=127933440 size=131072 end_off=128064512 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2725e01c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725e01c00 p_off=132127744 size=131072 end_off=132258816 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724ebec00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724ebec00 p_off=116124672 size=131072 end_off=116255744 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271eee0000 off=15597568 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271eee0000 p_off=15597568 size=131072 end_off=15728640 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f272531ec00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272531ec00 p_off=120712192 size=131072 end_off=120843264 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2725e21c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725e21c00 p_off=132258816 size=131072 end_off=132389888 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724edec00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724edec00 p_off=116255744 size=131072 end_off=116386816 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ef00000 off=15728640 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ef00000 p_off=15728640 size=131072 end_off=15859712 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f272533ec00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272533ec00 p_off=120843264 size=131072 end_off=120974336 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2725e41c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725e41c00 p_off=132389888 size=131072 end_off=132520960 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f2726241c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726241c00 p_off=136584192 size=131072 end_off=136715264 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ef20000 off=15859712 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ef20000 p_off=15859712 size=131072 end_off=15990784 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f272535ec00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724efec00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724efec00 p_off=116386816 size=131072 end_off=116517888 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2725e61c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725e61c00 p_off=132520960 size=131072 end_off=132652032 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f2726261c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726261c00 p_off=136715264 size=131072 end_off=136846336 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725a21c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725a21c00 p_off=128064512 size=131072 end_off=128195584 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272535ec00 p_off=120974336 size=131072 end_off=121105408 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ef40000 off=15990784 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ef40000 p_off=15990784 size=131072 end_off=16121856 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2725e81c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725e81c00 p_off=132652032 size=131072 end_off=132783104 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725a41c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725a41c00 p_off=128195584 size=131072 end_off=128326656 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f2726281c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726281c00 p_off=136846336 size=131072 end_off=136977408 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ef60000 off=16121856 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ef60000 p_off=16121856 size=131072 end_off=16252928 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724f1ec00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724f1ec00 p_off=116517888 size=131072 end_off=116648960 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725a61c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725a61c00 p_off=128326656 size=131072 end_off=128457728 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f27262a1c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27262a1c00 p_off=136977408 size=131072 end_off=137108480 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f272537ec00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272537ec00 p_off=121105408 size=131072 end_off=121236480 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724f3ec00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724f3ec00 p_off=116648960 size=131072 end_off=116780032 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f27262c1c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27262c1c00 p_off=137108480 size=131072 end_off=137239552 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f272539ec00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272539ec00 p_off=121236480 size=131072 end_off=121367552 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724f5ec00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724f5ec00 p_off=116780032 size=131072 end_off=116911104 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f27262e1c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27262e1c00 p_off=137239552 size=131072 end_off=137370624 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725a81c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725a81c00 p_off=128457728 size=131072 end_off=128588800 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724f7ec00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724f7ec00 p_off=116911104 size=131072 end_off=117042176 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f2726301c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726301c00 p_off=137370624 size=131072 end_off=137501696 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2725ea1c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725ea1c00 p_off=132783104 size=131072 end_off=132914176 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ef80000 off=16252928 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ef80000 p_off=16252928 size=131072 end_off=16384000 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725aa1c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725aa1c00 p_off=128588800 size=131072 end_off=128719872 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f2726321c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726321c00 p_off=137501696 size=131072 end_off=137632768 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2725ec1c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725ec1c00 p_off=132914176 size=131072 end_off=133045248 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f27253bec00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27253bec00 p_off=121367552 size=131072 end_off=121498624 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724f9ec00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724f9ec00 p_off=117042176 size=131072 end_off=117173248 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271efa0000 off=16384000 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271efa0000 p_off=16384000 size=131072 end_off=16515072 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2725ee1c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725ee1c00 p_off=133045248 size=131072 end_off=133176320 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f27253dec00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27253dec00 p_off=121498624 size=131072 end_off=121629696 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f2726341c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726341c00 p_off=137632768 size=131072 end_off=137763840 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2725f01c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725f01c00 p_off=133176320 size=131072 end_off=133307392 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271efc0000 off=16515072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271efc0000 p_off=16515072 size=131072 end_off=16646144 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724fbec00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724fbec00 p_off=117173248 size=131072 end_off=117304320 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f27253fec00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27253fec00 p_off=121629696 size=131072 end_off=121760768 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2725f21c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725f21c00 p_off=133307392 size=131072 end_off=133438464 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271efe0000 off=16646144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271efe0000 p_off=16646144 size=131072 end_off=16777216 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f2726361c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726361c00 p_off=137763840 size=131072 end_off=137894912 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724fdec00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724fdec00 p_off=117304320 size=131072 end_off=117435392 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2725f41c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725f41c00 p_off=133438464 size=131072 end_off=133569536 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f000000 off=16777216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f000000 p_off=16777216 size=131072 end_off=16908288 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725ac1c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725ac1c00 p_off=128719872 size=131072 end_off=128850944 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f2726381c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726381c00 p_off=137894912 size=131072 end_off=138025984 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f272541ec00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272541ec00 p_off=121760768 size=131072 end_off=121891840 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725ae1c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725ae1c00 p_off=128850944 size=131072 end_off=128982016 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f27263a1c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27263a1c00 p_off=138025984 size=131072 end_off=138157056 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f020000 off=16908288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f020000 p_off=16908288 size=131072 end_off=17039360 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2725f61c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725f61c00 p_off=133569536 size=131072 end_off=133700608 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f272543ec00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272543ec00 p_off=121891840 size=131072 end_off=122022912 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f27263c1c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27263c1c00 p_off=138157056 size=131072 end_off=138288128 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725b01c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725b01c00 p_off=128982016 size=131072 end_off=129113088 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f272545ec00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272545ec00 p_off=122022912 size=131072 end_off=122153984 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f040000 off=17039360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f040000 p_off=17039360 size=131072 end_off=17170432 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2725f81c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725f81c00 p_off=133700608 size=131072 end_off=133831680 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f27263e1c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27263e1c00 p_off=138288128 size=131072 end_off=138419200 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f2724ffec00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2724ffec00 p_off=117435392 size=131072 end_off=117566464 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725b21c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725b21c00 p_off=129113088 size=131072 end_off=129244160 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f060000 off=17170432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f060000 p_off=17170432 size=131072 end_off=17301504 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2725fa1c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725fa1c00 p_off=133831680 size=131072 end_off=133962752 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f2726401c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726401c00 p_off=138419200 size=131072 end_off=138550272 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800fef0 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f2724bbec00 dst1=0x7f272501ec00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272501ec00 p_off=117566464 size=131072 end_off=117697536 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725b41c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725b41c00 p_off=129244160 size=131072 end_off=129375232 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f080000 off=17301504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f080000 p_off=17301504 size=131072 end_off=17432576 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2725fc1c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725fc1c00 p_off=133962752 size=131072 end_off=134093824 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f2726421c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726421c00 p_off=138550272 size=131072 end_off=138681344 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010ec0 buffer=0x7f27b94d3ab0 data(host)=0xc000700000 dst0=0x7f27266c1c00 dst1=0x7f27266c1c00 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2725fe1c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725fe1c00 p_off=134093824 size=131072 end_off=134224896 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f2726441c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726441c00 p_off=138681344 size=131072 end_off=138812416 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725b61c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725b61c00 p_off=129375232 size=131072 end_off=129506304 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f0a0000 off=17432576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f0a0000 p_off=17432576 size=131072 end_off=17563648 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f272547ec00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272547ec00 p_off=122153984 size=131072 end_off=122285056 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2726001c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726001c00 p_off=134224896 size=131072 end_off=134355968 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f2726461c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726461c00 p_off=138812416 size=131072 end_off=138943488 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010060 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272503ec00 dst1=0x7f272549ec00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272549ec00 p_off=122285056 size=131072 end_off=122416128 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725b81c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725b81c00 p_off=129506304 size=131072 end_off=129637376 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f0c0000 off=17563648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f0c0000 p_off=17563648 size=131072 end_off=17694720 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f2726481c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725ba1c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726481c00 p_off=138943488 size=131072 end_off=139074560 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27266c1c00 p_off=141302784 size=3072 end_off=141305856 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011030 buffer=0x7f27b94d3ab0 data(host)=0xc000720000 dst0=0x7f27266c2800 dst1=0x7f27266c2800 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27266c2800 p_off=141305856 size=3072 end_off=141308928 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f27264a1c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27264a1c00 p_off=139074560 size=131072 end_off=139205632 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80111a0 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f27266c3400 dst1=0x7f27266c3400 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27266c3400 p_off=141308928 size=3072 end_off=141312000 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f0e0000 off=17694720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f0e0000 p_off=17694720 size=131072 end_off=17825792 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2726021c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726021c00 p_off=134355968 size=131072 end_off=134487040 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f27264c1c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27264c1c00 p_off=139205632 size=131072 end_off=139336704 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f100000 off=17825792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f100000 p_off=17825792 size=131072 end_off=17956864 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011310 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f27266c4000 dst1=0x7f27266c4000 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27266c4000 p_off=141312000 size=3072 end_off=141315072 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f27266c4c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27266c4c00 p_off=141315072 size=131072 end_off=141446144 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2726041c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726041c00 p_off=134487040 size=131072 end_off=134618112 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f27264e1c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27264e1c00 p_off=139336704 size=131072 end_off=139467776 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f120000 off=17956864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f120000 p_off=17956864 size=131072 end_off=18087936 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f27266e4c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27266e4c00 p_off=141446144 size=131072 end_off=141577216 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f2726501c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726501c00 p_off=139467776 size=131072 end_off=139598848 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80115f0 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2726a24c00 dst1=0x7f2726a24c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726a24c00 p_off=144854016 size=131072 end_off=144985088 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725ba1c00 p_off=129637376 size=131072 end_off=129768448 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f2726521c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725bc1c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2726061c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725bc1c00 p_off=129768448 size=131072 end_off=129899520 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726061c00 p_off=134618112 size=131072 end_off=134749184 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726521c00 p_off=139598848 size=131072 end_off=139729920 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f2726704c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726704c00 p_off=141577216 size=131072 end_off=141708288 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f140000 off=18087936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f140000 p_off=18087936 size=131072 end_off=18219008 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f2726541c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726541c00 p_off=139729920 size=131072 end_off=139860992 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80115f0 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2726a24c00 dst1=0x7f2726a44c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726a44c00 p_off=144985088 size=131072 end_off=145116160 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f160000 off=18219008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2726081c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726081c00 p_off=134749184 size=131072 end_off=134880256 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f160000 p_off=18219008 size=131072 end_off=18350080 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f2726724c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726724c00 p_off=141708288 size=131072 end_off=141839360 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80115f0 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2726a24c00 dst1=0x7f2726a64c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726a64c00 p_off=145116160 size=131072 end_off=145247232 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f2726561c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726561c00 p_off=139860992 size=131072 end_off=139992064 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f27260a1c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27260a1c00 p_off=134880256 size=131072 end_off=135011328 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f2726744c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726744c00 p_off=141839360 size=131072 end_off=141970432 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f2726581c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726581c00 p_off=139992064 size=131072 end_off=140123136 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f27260c1c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27260c1c00 p_off=135011328 size=131072 end_off=135142400 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725be1c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725be1c00 p_off=129899520 size=131072 end_off=130030592 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f27265a1c00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27265a1c00 p_off=140123136 size=131072 end_off=140254208 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725c01c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725c01c00 p_off=130030592 size=131072 end_off=130161664 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f2726764c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726764c00 p_off=141970432 size=131072 end_off=142101504 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f27260e1c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27260e1c00 p_off=135142400 size=131072 end_off=135273472 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f27265c1c00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27265c1c00 p_off=140254208 size=131072 end_off=140385280 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f180000 off=18350080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f180000 p_off=18350080 size=131072 end_off=18481152 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725c21c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725c21c00 p_off=130161664 size=131072 end_off=130292736 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f2726784c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726784c00 p_off=142101504 size=131072 end_off=142232576 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80115f0 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2726a24c00 dst1=0x7f2726a84c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726a84c00 p_off=145247232 size=131072 end_off=145378304 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2726101c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726101c00 p_off=135273472 size=131072 end_off=135404544 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f27265e1c00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27265e1c00 p_off=140385280 size=131072 end_off=140516352 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f1a0000 off=18481152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f1a0000 p_off=18481152 size=131072 end_off=18612224 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f27267a4c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27267a4c00 p_off=142232576 size=131072 end_off=142363648 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80115f0 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2726a24c00 dst1=0x7f2726aa4c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726aa4c00 p_off=145378304 size=131072 end_off=145509376 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f1c0000 off=18612224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f1c0000 p_off=18612224 size=131072 end_off=18743296 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f2726601c00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726601c00 p_off=140516352 size=131072 end_off=140647424 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f27267c4c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27267c4c00 p_off=142363648 size=131072 end_off=142494720 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2726121c00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725c41c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725c41c00 p_off=130292736 size=131072 end_off=130423808 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f1e0000 off=18743296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f1e0000 p_off=18743296 size=131072 end_off=18874368 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f2726621c00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726621c00 p_off=140647424 size=131072 end_off=140778496 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f27267e4c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27267e4c00 p_off=142494720 size=131072 end_off=142625792 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80115f0 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2726a24c00 dst1=0x7f2726ac4c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726ac4c00 p_off=145509376 size=131072 end_off=145640448 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726121c00 p_off=135404544 size=131072 end_off=135535616 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f2726641c00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726641c00 p_off=140778496 size=131072 end_off=140909568 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725c61c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725c61c00 p_off=130423808 size=131072 end_off=130554880 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f2726804c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726804c00 p_off=142625792 size=131072 end_off=142756864 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f2726661c00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f200000 off=18874368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f200000 p_off=18874368 size=131072 end_off=19005440 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726661c00 p_off=140909568 size=131072 end_off=141040640 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2726141c00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726141c00 p_off=135535616 size=131072 end_off=135666688 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725c81c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725c81c00 p_off=130554880 size=131072 end_off=130685952 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f2726824c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726824c00 p_off=142756864 size=131072 end_off=142887936 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2726161c00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726161c00 p_off=135666688 size=131072 end_off=135797760 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725ca1c00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725ca1c00 p_off=130685952 size=131072 end_off=130817024 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f2726681c00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726681c00 p_off=141040640 size=131072 end_off=141171712 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80115f0 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2726a24c00 dst1=0x7f2726ae4c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f2726844c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726844c00 p_off=142887936 size=131072 end_off=143019008 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726ae4c00 p_off=145640448 size=131072 end_off=145771520 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010d50 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f2726241c00 dst1=0x7f27266a1c00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27266a1c00 p_off=141171712 size=131072 end_off=141302784 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f220000 off=19005440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f220000 p_off=19005440 size=131072 end_off=19136512 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f2726864c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726864c00 p_off=143019008 size=131072 end_off=143150080 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80115f0 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2726a24c00 dst1=0x7f2726b04c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726b04c00 p_off=145771520 size=131072 end_off=145902592 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2726181c00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726181c00 p_off=135797760 size=131072 end_off=135928832 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725cc1c00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725cc1c00 p_off=130817024 size=131072 end_off=130948096 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f2726884c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726884c00 p_off=143150080 size=131072 end_off=143281152 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80115f0 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f2726a24c00 dst1=0x7f2726b24c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726b24c00 p_off=145902592 size=131072 end_off=146033664 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f240000 off=19136512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f240000 p_off=19136512 size=131072 end_off=19267584 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726b44c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726b44c00 p_off=146033664 size=131072 end_off=146164736 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f27268a4c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27268a4c00 p_off=143281152 size=131072 end_off=143412224 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f27261a1c00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27261a1c00 p_off=135928832 size=131072 end_off=136059904 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f2726fc4c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726fc4c00 p_off=150752256 size=131072 end_off=150883328 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f27268c4c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27268c4c00 p_off=143412224 size=131072 end_off=143543296 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f27261c1c00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726b64c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726b64c00 p_off=146164736 size=131072 end_off=146295808 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f2726fe4c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726fe4c00 p_off=150883328 size=131072 end_off=151014400 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f27268e4c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27268e4c00 p_off=143543296 size=131072 end_off=143674368 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f260000 off=19267584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f260000 p_off=19267584 size=131072 end_off=19398656 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725ce1c00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725ce1c00 p_off=130948096 size=131072 end_off=131079168 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726b84c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726b84c00 p_off=146295808 size=131072 end_off=146426880 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f280000 off=19398656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f280000 p_off=19398656 size=131072 end_off=19529728 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f2727004c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727004c00 p_off=151014400 size=131072 end_off=151145472 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726ba4c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726ba4c00 p_off=146426880 size=131072 end_off=146557952 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f2726904c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726904c00 p_off=143674368 size=131072 end_off=143805440 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f2727024c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727024c00 p_off=151145472 size=131072 end_off=151276544 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726bc4c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726bc4c00 p_off=146557952 size=131072 end_off=146689024 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27261c1c00 p_off=136059904 size=131072 end_off=136190976 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f2726924c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726924c00 p_off=143805440 size=131072 end_off=143936512 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f2727044c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727044c00 p_off=151276544 size=131072 end_off=151407616 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726be4c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726be4c00 p_off=146689024 size=131072 end_off=146820096 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f27261e1c00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f2726944c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726944c00 p_off=143936512 size=131072 end_off=144067584 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27261e1c00 p_off=136190976 size=131072 end_off=136322048 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f2a0000 off=19529728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f2a0000 p_off=19529728 size=131072 end_off=19660800 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f2727064c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727064c00 p_off=151407616 size=131072 end_off=151538688 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726c04c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726c04c00 p_off=146820096 size=131072 end_off=146951168 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f2726964c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726964c00 p_off=144067584 size=131072 end_off=144198656 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725d01c00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725d01c00 p_off=131079168 size=131072 end_off=131210240 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f2c0000 off=19660800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f2c0000 p_off=19660800 size=131072 end_off=19791872 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2726201c00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726201c00 p_off=136322048 size=131072 end_off=136453120 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726c24c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726c24c00 p_off=146951168 size=131072 end_off=147082240 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f2727084c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727084c00 p_off=151538688 size=131072 end_off=151669760 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725d21c00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725d21c00 p_off=131210240 size=131072 end_off=131341312 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f2e0000 off=19791872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f2e0000 p_off=19791872 size=131072 end_off=19922944 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f27270a4c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27270a4c00 p_off=151669760 size=131072 end_off=151800832 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726c44c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726c44c00 p_off=147082240 size=131072 end_off=147213312 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725d41c00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725d41c00 p_off=131341312 size=131072 end_off=131472384 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f2726984c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726984c00 p_off=144198656 size=131072 end_off=144329728 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726c64c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726c64c00 p_off=147213312 size=131072 end_off=147344384 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010be0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f2725dc1c00 dst1=0x7f2726221c00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726221c00 p_off=136453120 size=131072 end_off=136584192 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f300000 off=19922944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f300000 p_off=19922944 size=131072 end_off=20054016 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f27269a4c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27269a4c00 p_off=144329728 size=131072 end_off=144460800 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726c84c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726c84c00 p_off=147344384 size=131072 end_off=147475456 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f27270c4c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27270c4c00 p_off=151800832 size=131072 end_off=151931904 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f27269c4c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27269c4c00 p_off=144460800 size=131072 end_off=144591872 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726ca4c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726ca4c00 p_off=147475456 size=131072 end_off=147606528 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f27270e4c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27270e4c00 p_off=151931904 size=131072 end_off=152062976 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f27269e4c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27269e4c00 p_off=144591872 size=131072 end_off=144722944 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726cc4c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726cc4c00 p_off=147606528 size=131072 end_off=147737600 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f2727104c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727104c00 p_off=152062976 size=131072 end_off=152194048 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725d61c00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725d61c00 p_off=131472384 size=131072 end_off=131603456 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f320000 off=20054016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f320000 p_off=20054016 size=131072 end_off=20185088 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725d81c00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725d81c00 p_off=131603456 size=131072 end_off=131734528 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f340000 off=20185088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f340000 p_off=20185088 size=131072 end_off=20316160 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8010a70 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2725941c00 dst1=0x7f2725da1c00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2725da1c00 p_off=131734528 size=131072 end_off=131865600 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f360000 off=20316160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f360000 p_off=20316160 size=131072 end_off=20447232 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f2727444c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727444c00 p_off=155470848 size=131072 end_off=155601920 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011bb0 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f27278c4c00 dst1=0x7f27278c4c00 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27278c4c00 p_off=160189440 size=3072 end_off=160192512 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f2727464c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727464c00 p_off=155601920 size=131072 end_off=155732992 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011d20 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f27278c5800 dst1=0x7f27278c5800 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27278c5800 p_off=160192512 size=3072 end_off=160195584 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f2727124c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727124c00 p_off=152194048 size=131072 end_off=152325120 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011e90 buffer=0x7f27b94d3ab0 data(host)=0xc0008ca000 dst0=0x7f27278c6400 dst1=0x7f27278c6400 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27278c6400 p_off=160195584 size=3072 end_off=160198656 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011480 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f27266c4c00 dst1=0x7f2726a04c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f2727484c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727484c00 p_off=155732992 size=131072 end_off=155864064 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726a04c00 p_off=144722944 size=131072 end_off=144854016 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f380000 off=20447232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f380000 p_off=20447232 size=131072 end_off=20578304 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f27274a4c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27274a4c00 p_off=155864064 size=131072 end_off=155995136 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f27278c7c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f3a0000 off=20578304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f3a0000 p_off=20578304 size=131072 end_off=20709376 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f27274c4c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27274c4c00 p_off=155995136 size=131072 end_off=156126208 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726ce4c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f2727144c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27278c7c00 p_off=160201728 size=131072 end_off=160332800 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727144c00 p_off=152325120 size=131072 end_off=152456192 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726ce4c00 p_off=147737600 size=131072 end_off=147868672 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f3c0000 off=20709376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f3c0000 p_off=20709376 size=131072 end_off=20840448 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f27278e7c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27278e7c00 p_off=160332800 size=131072 end_off=160463872 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f2727164c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727164c00 p_off=152456192 size=131072 end_off=152587264 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f27274e4c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27274e4c00 p_off=156126208 size=131072 end_off=156257280 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f3e0000 off=20840448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f3e0000 p_off=20840448 size=131072 end_off=20971520 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f2727907c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727907c00 p_off=160463872 size=131072 end_off=160594944 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f2727184c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727184c00 p_off=152587264 size=131072 end_off=152718336 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f2727504c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727504c00 p_off=156257280 size=131072 end_off=156388352 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f400000 off=20971520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f400000 p_off=20971520 size=131072 end_off=21102592 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f2727927c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727927c00 p_off=160594944 size=131072 end_off=160726016 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f27271a4c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27271a4c00 p_off=152718336 size=131072 end_off=152849408 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f2727524c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727524c00 p_off=156388352 size=131072 end_off=156519424 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f420000 off=21102592 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f420000 p_off=21102592 size=131072 end_off=21233664 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f2727947c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727947c00 p_off=160726016 size=131072 end_off=160857088 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f27271c4c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27271c4c00 p_off=152849408 size=131072 end_off=152980480 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f2727544c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727544c00 p_off=156519424 size=131072 end_off=156650496 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f440000 off=21233664 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f440000 p_off=21233664 size=131072 end_off=21364736 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f2727967c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727967c00 p_off=160857088 size=131072 end_off=160988160 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f27271e4c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27271e4c00 p_off=152980480 size=131072 end_off=153111552 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f2727564c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727564c00 p_off=156650496 size=131072 end_off=156781568 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f460000 off=21364736 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f460000 p_off=21364736 size=131072 end_off=21495808 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f2727987c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727987c00 p_off=160988160 size=131072 end_off=161119232 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f2727204c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727204c00 p_off=153111552 size=131072 end_off=153242624 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f2727584c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727584c00 p_off=156781568 size=131072 end_off=156912640 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f480000 off=21495808 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f480000 p_off=21495808 size=131072 end_off=21626880 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f27279a7c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27279a7c00 p_off=161119232 size=131072 end_off=161250304 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f2727224c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727224c00 p_off=153242624 size=131072 end_off=153373696 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f27275a4c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27275a4c00 p_off=156912640 size=131072 end_off=157043712 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f4a0000 off=21626880 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f4a0000 p_off=21626880 size=131072 end_off=21757952 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f2727244c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727244c00 p_off=153373696 size=131072 end_off=153504768 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012000 buffer=0x7f27b94d3ab0 data(host)=0xc00090a000 dst0=0x7f27278c7000 dst1=0x7f27278c7000 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27278c7000 p_off=160198656 size=3072 end_off=160201728 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f4c0000 off=21757952 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f4c0000 p_off=21757952 size=131072 end_off=21889024 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f2727264c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727264c00 p_off=153504768 size=131072 end_off=153635840 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726d04c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726d04c00 p_off=147868672 size=131072 end_off=147999744 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f4e0000 off=21889024 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f4e0000 p_off=21889024 size=131072 end_off=22020096 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80122e0 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f2727c27c00 dst1=0x7f2727c27c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727c27c00 p_off=163740672 size=131072 end_off=163871744 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f2727284c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727284c00 p_off=153635840 size=131072 end_off=153766912 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726d24c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726d24c00 p_off=147999744 size=131072 end_off=148130816 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f500000 off=22020096 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f500000 p_off=22020096 size=131072 end_off=22151168 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80122e0 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f2727c27c00 dst1=0x7f2727c47c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727c47c00 p_off=163871744 size=131072 end_off=164002816 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f27272a4c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27272a4c00 p_off=153766912 size=131072 end_off=153897984 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726d44c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726d44c00 p_off=148130816 size=131072 end_off=148261888 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f520000 off=22151168 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f520000 p_off=22151168 size=131072 end_off=22282240 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80122e0 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f2727c27c00 dst1=0x7f2727c67c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727c67c00 p_off=164002816 size=131072 end_off=164133888 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f27272c4c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27272c4c00 p_off=153897984 size=131072 end_off=154029056 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726d64c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726d64c00 p_off=148261888 size=131072 end_off=148392960 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f27275c4c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27275c4c00 p_off=157043712 size=131072 end_off=157174784 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f540000 off=22282240 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f540000 p_off=22282240 size=131072 end_off=22413312 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80122e0 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f2727c27c00 dst1=0x7f2727c87c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727c87c00 p_off=164133888 size=131072 end_off=164264960 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f27272e4c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27272e4c00 p_off=154029056 size=131072 end_off=154160128 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f560000 off=22413312 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f560000 p_off=22413312 size=131072 end_off=22544384 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f27275e4c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27275e4c00 p_off=157174784 size=131072 end_off=157305856 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726d84c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726d84c00 p_off=148392960 size=131072 end_off=148524032 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80122e0 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f2727c27c00 dst1=0x7f2727ca7c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727ca7c00 p_off=164264960 size=131072 end_off=164396032 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f2727304c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727304c00 p_off=154160128 size=131072 end_off=154291200 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80122e0 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f2727c27c00 dst1=0x7f2727cc7c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727cc7c00 p_off=164396032 size=131072 end_off=164527104 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726da4c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726da4c00 p_off=148524032 size=131072 end_off=148655104 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80122e0 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f2727c27c00 dst1=0x7f2727ce7c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727ce7c00 p_off=164527104 size=131072 end_off=164658176 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726dc4c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726dc4c00 p_off=148655104 size=131072 end_off=148786176 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f2727604c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f580000 off=22544384 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f580000 p_off=22544384 size=131072 end_off=22675456 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727604c00 p_off=157305856 size=131072 end_off=157436928 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80122e0 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f2727c27c00 dst1=0x7f2727d07c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727d07c00 p_off=164658176 size=131072 end_off=164789248 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f2727324c00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727324c00 p_off=154291200 size=131072 end_off=154422272 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f2727624c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727624c00 p_off=157436928 size=131072 end_off=157568000 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f5a0000 off=22675456 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f5a0000 p_off=22675456 size=131072 end_off=22806528 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80122e0 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f2727c27c00 dst1=0x7f2727d27c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727d27c00 p_off=164789248 size=131072 end_off=164920320 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f27279c7c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27279c7c00 p_off=161250304 size=131072 end_off=161381376 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726de4c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726de4c00 p_off=148786176 size=131072 end_off=148917248 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f5c0000 off=22806528 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f5c0000 p_off=22806528 size=131072 end_off=22937600 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f2727644c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727644c00 p_off=157568000 size=131072 end_off=157699072 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f27279e7c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27279e7c00 p_off=161381376 size=131072 end_off=161512448 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726e04c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726e04c00 p_off=148917248 size=131072 end_off=149048320 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f2727344c00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727344c00 p_off=154422272 size=131072 end_off=154553344 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f5e0000 off=22937600 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f5e0000 p_off=22937600 size=131072 end_off=23068672 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f2727a07c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727a07c00 p_off=161512448 size=131072 end_off=161643520 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f2727364c00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727364c00 p_off=154553344 size=131072 end_off=154684416 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f600000 off=23068672 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f600000 p_off=23068672 size=131072 end_off=23199744 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f2727a27c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727a27c00 p_off=161643520 size=131072 end_off=161774592 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f2727384c00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727384c00 p_off=154684416 size=131072 end_off=154815488 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f620000 off=23199744 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f620000 p_off=23199744 size=131072 end_off=23330816 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f2727a47c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727a47c00 p_off=161774592 size=131072 end_off=161905664 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f27273a4c00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27273a4c00 p_off=154815488 size=131072 end_off=154946560 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f640000 off=23330816 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f640000 p_off=23330816 size=131072 end_off=23461888 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f2727a67c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727a67c00 p_off=161905664 size=131072 end_off=162036736 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f27273c4c00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27273c4c00 p_off=154946560 size=131072 end_off=155077632 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f660000 off=23461888 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f660000 p_off=23461888 size=131072 end_off=23592960 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f2727a87c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727a87c00 p_off=162036736 size=131072 end_off=162167808 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f27273e4c00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27273e4c00 p_off=155077632 size=131072 end_off=155208704 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f680000 off=23592960 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f680000 p_off=23592960 size=131072 end_off=23724032 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f2727aa7c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727aa7c00 p_off=162167808 size=131072 end_off=162298880 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f6a0000 off=23724032 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f6a0000 p_off=23724032 size=131072 end_off=23855104 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726e24c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726e24c00 p_off=149048320 size=131072 end_off=149179392 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2727d47c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727d47c00 p_off=164920320 size=131072 end_off=165051392 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726e44c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726e44c00 p_off=149179392 size=131072 end_off=149310464 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f6c0000 off=23855104 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f6c0000 p_off=23855104 size=131072 end_off=23986176 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2727d67c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727d67c00 p_off=165051392 size=131072 end_off=165182464 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726e64c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726e64c00 p_off=149310464 size=131072 end_off=149441536 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f2727664c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727664c00 p_off=157699072 size=131072 end_off=157830144 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f6e0000 off=23986176 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f6e0000 p_off=23986176 size=131072 end_off=24117248 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f2727ac7c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727ac7c00 p_off=162298880 size=131072 end_off=162429952 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f2727684c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727684c00 p_off=157830144 size=131072 end_off=157961216 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f700000 off=24117248 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f700000 p_off=24117248 size=131072 end_off=24248320 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f2727ae7c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727ae7c00 p_off=162429952 size=131072 end_off=162561024 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726e84c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726e84c00 p_off=149441536 size=131072 end_off=149572608 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f720000 off=24248320 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f720000 p_off=24248320 size=131072 end_off=24379392 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f2727b07c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727b07c00 p_off=162561024 size=131072 end_off=162692096 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726ea4c00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726ea4c00 p_off=149572608 size=131072 end_off=149703680 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f740000 off=24379392 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f740000 p_off=24379392 size=131072 end_off=24510464 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726ec4c00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726ec4c00 p_off=149703680 size=131072 end_off=149834752 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2727d87c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727d87c00 p_off=165182464 size=131072 end_off=165313536 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f760000 off=24510464 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f760000 p_off=24510464 size=131072 end_off=24641536 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2727da7c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727da7c00 p_off=165313536 size=131072 end_off=165444608 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f27276a4c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27276a4c00 p_off=157961216 size=131072 end_off=158092288 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2727dc7c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727dc7c00 p_off=165444608 size=131072 end_off=165575680 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f27276c4c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27276c4c00 p_off=158092288 size=131072 end_off=158223360 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2727de7c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727de7c00 p_off=165575680 size=131072 end_off=165706752 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f27276e4c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27276e4c00 p_off=158223360 size=131072 end_off=158354432 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2727e07c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727e07c00 p_off=165706752 size=131072 end_off=165837824 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f2727b27c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727b27c00 p_off=162692096 size=131072 end_off=162823168 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f780000 off=24641536 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f2727704c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727704c00 p_off=158354432 size=131072 end_off=158485504 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f780000 p_off=24641536 size=131072 end_off=24772608 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f2727b47c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727b47c00 p_off=162823168 size=131072 end_off=162954240 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f2727724c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727724c00 p_off=158485504 size=131072 end_off=158616576 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f2727b67c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727b67c00 p_off=162954240 size=131072 end_off=163085312 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f7a0000 off=24772608 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f7a0000 p_off=24772608 size=131072 end_off=24903680 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f2727744c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727744c00 p_off=158616576 size=131072 end_off=158747648 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f2727b87c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727b87c00 p_off=163085312 size=131072 end_off=163216384 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f7c0000 off=24903680 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f7c0000 p_off=24903680 size=131072 end_off=25034752 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f2727764c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727764c00 p_off=158747648 size=131072 end_off=158878720 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2727e27c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727e27c00 p_off=165837824 size=131072 end_off=165968896 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f7e0000 off=25034752 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f7e0000 p_off=25034752 size=131072 end_off=25165824 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f2727784c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727784c00 p_off=158878720 size=131072 end_off=159009792 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2727e47c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727e47c00 p_off=165968896 size=131072 end_off=166099968 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f800000 off=25165824 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f800000 p_off=25165824 size=131072 end_off=25296896 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f27277a4c00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27277a4c00 p_off=159009792 size=131072 end_off=159140864 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2727e67c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727e67c00 p_off=166099968 size=131072 end_off=166231040 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f820000 off=25296896 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f820000 p_off=25296896 size=131072 end_off=25427968 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f27277c4c00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27277c4c00 p_off=159140864 size=131072 end_off=159271936 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726ee4c00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726ee4c00 p_off=149834752 size=131072 end_off=149965824 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f2727ba7c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727ba7c00 p_off=163216384 size=131072 end_off=163347456 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f840000 off=25427968 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f840000 p_off=25427968 size=131072 end_off=25559040 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726f04c00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726f04c00 p_off=149965824 size=131072 end_off=150096896 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f2727bc7c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727bc7c00 p_off=163347456 size=131072 end_off=163478528 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2727e87c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727e87c00 p_off=166231040 size=131072 end_off=166362112 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f860000 off=25559040 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f860000 p_off=25559040 size=131072 end_off=25690112 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726f24c00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726f24c00 p_off=150096896 size=131072 end_off=150227968 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2727ea7c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727ea7c00 p_off=166362112 size=131072 end_off=166493184 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f880000 off=25690112 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f880000 p_off=25690112 size=131072 end_off=25821184 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726f44c00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726f44c00 p_off=150227968 size=131072 end_off=150359040 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2727ec7c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727ec7c00 p_off=166493184 size=131072 end_off=166624256 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f8a0000 off=25821184 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f8a0000 p_off=25821184 size=131072 end_off=25952256 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726f64c00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726f64c00 p_off=150359040 size=131072 end_off=150490112 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f2727be7c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727be7c00 p_off=163478528 size=131072 end_off=163609600 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726f84c00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726f84c00 p_off=150490112 size=131072 end_off=150621184 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012170 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f27278c7c00 dst1=0x7f2727c07c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727c07c00 p_off=163609600 size=131072 end_off=163740672 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f8c0000 off=25952256 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f8c0000 p_off=25952256 size=131072 end_off=26083328 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011760 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f2726b44c00 dst1=0x7f2726fa4c00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2726fa4c00 p_off=150621184 size=131072 end_off=150752256 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f8e0000 off=26083328 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f8e0000 p_off=26083328 size=131072 end_off=26214400 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f27281c7c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27281c7c00 p_off=169638912 size=131072 end_off=169769984 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f2727404c00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727404c00 p_off=155208704 size=131072 end_off=155339776 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f27277e4c00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27277e4c00 p_off=159271936 size=131072 end_off=159403008 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80118d0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f2726fc4c00 dst1=0x7f2727424c00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f27281e7c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27281e7c00 p_off=169769984 size=131072 end_off=169901056 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727424c00 p_off=155339776 size=131072 end_off=155470848 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f2727804c00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727804c00 p_off=159403008 size=131072 end_off=159534080 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f2728207c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728207c00 p_off=169901056 size=131072 end_off=170032128 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2727ee7c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727ee7c00 p_off=166624256 size=131072 end_off=166755328 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80128a0 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f2728ac7c00 dst1=0x7f2728ac7c00 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728ac7c00 p_off=179076096 size=3072 end_off=179079168 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f2727824c00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727824c00 p_off=159534080 size=131072 end_off=159665152 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2727f07c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727f07c00 p_off=166755328 size=131072 end_off=166886400 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f2727844c00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727844c00 p_off=159665152 size=131072 end_off=159796224 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012a10 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f2728ac8800 dst1=0x7f2728ac8800 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728ac8800 p_off=179079168 size=3072 end_off=179082240 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012b80 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f2728ac9400 dst1=0x7f2728ac9400 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728ac9400 p_off=179082240 size=3072 end_off=179085312 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2727f27c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727f27c00 p_off=166886400 size=131072 end_off=167017472 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f2727864c00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727864c00 p_off=159796224 size=131072 end_off=159927296 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012cf0 buffer=0x7f27b94d3ab0 data(host)=0xc000a2a000 dst0=0x7f2728aca000 dst1=0x7f2728aca000 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728aca000 p_off=179085312 size=3072 end_off=179088384 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728acac00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728acac00 p_off=179088384 size=131072 end_off=179219456 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f2728227c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f2728647c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728647c00 p_off=174357504 size=131072 end_off=174488576 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728227c00 p_off=170032128 size=131072 end_off=170163200 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728aeac00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728aeac00 p_off=179219456 size=131072 end_off=179350528 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f2728667c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728667c00 p_off=174488576 size=131072 end_off=174619648 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f2728247c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728247c00 p_off=170163200 size=131072 end_off=170294272 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728b0ac00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728b0ac00 p_off=179350528 size=131072 end_off=179481600 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f2728687c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728687c00 p_off=174619648 size=131072 end_off=174750720 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f2728267c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728267c00 p_off=170294272 size=131072 end_off=170425344 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728b2ac00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728b2ac00 p_off=179481600 size=131072 end_off=179612672 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f27286a7c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27286a7c00 p_off=174750720 size=131072 end_off=174881792 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f2728287c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728287c00 p_off=170425344 size=131072 end_off=170556416 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728b4ac00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728b4ac00 p_off=179612672 size=131072 end_off=179743744 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f900000 off=26214400 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f900000 p_off=26214400 size=131072 end_off=26345472 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2727f47c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727f47c00 p_off=167017472 size=131072 end_off=167148544 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f920000 off=26345472 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f920000 p_off=26345472 size=131072 end_off=26476544 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2727f67c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727f67c00 p_off=167148544 size=131072 end_off=167279616 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f940000 off=26476544 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f940000 p_off=26476544 size=131072 end_off=26607616 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2727f87c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727f87c00 p_off=167279616 size=131072 end_off=167410688 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728b6ac00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728b6ac00 p_off=179743744 size=131072 end_off=179874816 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f960000 off=26607616 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f960000 p_off=26607616 size=131072 end_off=26738688 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2727fa7c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727fa7c00 p_off=167410688 size=131072 end_off=167541760 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728b8ac00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728b8ac00 p_off=179874816 size=131072 end_off=180005888 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2727fc7c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727fc7c00 p_off=167541760 size=131072 end_off=167672832 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2727fe7c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727fe7c00 p_off=167672832 size=131072 end_off=167803904 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f27282a7c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27282a7c00 p_off=170556416 size=131072 end_off=170687488 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728baac00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2728007c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728007c00 p_off=167803904 size=131072 end_off=167934976 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f27286c7c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27286c7c00 p_off=174881792 size=131072 end_off=175012864 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f2727884c00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2727884c00 p_off=159927296 size=131072 end_off=160058368 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f27282c7c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27282c7c00 p_off=170687488 size=131072 end_off=170818560 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728baac00 p_off=180005888 size=131072 end_off=180136960 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2728027c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728027c00 p_off=167934976 size=131072 end_off=168066048 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f27286e7c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27286e7c00 p_off=175012864 size=131072 end_off=175143936 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f2728707c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728707c00 p_off=175143936 size=131072 end_off=175275008 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2728047c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728047c00 p_off=168066048 size=131072 end_off=168197120 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8011a40 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f2727444c00 dst1=0x7f27278a4c00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27278a4c00 p_off=160058368 size=131072 end_off=160189440 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f980000 off=26738688 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f980000 p_off=26738688 size=131072 end_off=26869760 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728bcac00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728bcac00 p_off=180136960 size=131072 end_off=180268032 OOB=0
[GGML-CUDA-DIAG] cuCtxGetCurrent BAD cr=0 CUDA_SUCCESS no error ctx=(nil)
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f9a0000 off=26869760 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f27282e7c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f2728727c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] cuMemGetAddressRange FAILED cr=201 CUDA_ERROR_INVALID_CONTEXT invalid device context p=0x7f27282e7c00
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728727c00 p_off=175275008 size=131072 end_off=175406080 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012fd0 buffer=0x7f27b94d3ab0 data(host)=0xc000aca000 dst0=0x7f2728e2ac00 dst1=0x7f2728e2ac00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728e2ac00 p_off=182627328 size=131072 end_off=182758400 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728beac00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728beac00 p_off=180268032 size=131072 end_off=180399104 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2728067c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728067c00 p_off=168197120 size=131072 end_off=168328192 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f9a0000 p_off=26869760 size=131072 end_off=27000832 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f2728747c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728747c00 p_off=175406080 size=131072 end_off=175537152 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f2728307c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728307c00 p_off=170949632 size=131072 end_off=171080704 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2728087c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728087c00 p_off=168328192 size=131072 end_off=168459264 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f2728767c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728767c00 p_off=175537152 size=131072 end_off=175668224 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f9c0000 off=27000832 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f9c0000 p_off=27000832 size=131072 end_off=27131904 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728c0ac00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728c0ac00 p_off=180399104 size=131072 end_off=180530176 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012fd0 buffer=0x7f27b94d3ab0 data(host)=0xc000aca000 dst0=0x7f2728e2ac00 dst1=0x7f2728e4ac00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728e4ac00 p_off=182758400 size=131072 end_off=182889472 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f2728327c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728327c00 p_off=171080704 size=131072 end_off=171211776 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f2728787c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728787c00 p_off=175668224 size=131072 end_off=175799296 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f2728347c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728347c00 p_off=171211776 size=131072 end_off=171342848 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271f9e0000 off=27131904 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271f9e0000 p_off=27131904 size=131072 end_off=27262976 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012fd0 buffer=0x7f27b94d3ab0 data(host)=0xc000aca000 dst0=0x7f2728e2ac00 dst1=0x7f2728e6ac00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728e6ac00 p_off=182889472 size=131072 end_off=183020544 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f27280a7c00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27280a7c00 p_off=168459264 size=131072 end_off=168590336 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f2728367c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728367c00 p_off=171342848 size=131072 end_off=171473920 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f27287a7c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27287a7c00 p_off=175799296 size=131072 end_off=175930368 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728c2ac00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728c2ac00 p_off=180530176 size=131072 end_off=180661248 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f2728387c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728387c00 p_off=171473920 size=131072 end_off=171604992 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f27287c7c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27287c7c00 p_off=175930368 size=131072 end_off=176061440 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728c4ac00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728c4ac00 p_off=180661248 size=131072 end_off=180792320 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f27280c7c00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27280c7c00 p_off=168590336 size=131072 end_off=168721408 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f27283a7c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27283a7c00 p_off=171604992 size=131072 end_off=171736064 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fa00000 off=27262976 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fa00000 p_off=27262976 size=131072 end_off=27394048 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f27287e7c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27287e7c00 p_off=176061440 size=131072 end_off=176192512 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012fd0 buffer=0x7f27b94d3ab0 data(host)=0xc000aca000 dst0=0x7f2728e2ac00 dst1=0x7f2728e8ac00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728e8ac00 p_off=183020544 size=131072 end_off=183151616 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fa20000 off=27394048 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fa20000 p_off=27394048 size=131072 end_off=27525120 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f27283c7c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27283c7c00 p_off=171736064 size=131072 end_off=171867136 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f27280e7c00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27280e7c00 p_off=168721408 size=131072 end_off=168852480 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f2728807c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728807c00 p_off=176192512 size=131072 end_off=176323584 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012fd0 buffer=0x7f27b94d3ab0 data(host)=0xc000aca000 dst0=0x7f2728e2ac00 dst1=0x7f2728eaac00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728eaac00 p_off=183151616 size=131072 end_off=183282688 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f27283e7c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27283e7c00 p_off=171867136 size=131072 end_off=171998208 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f2728827c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728827c00 p_off=176323584 size=131072 end_off=176454656 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fa40000 off=27525120 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fa40000 p_off=27525120 size=131072 end_off=27656192 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2728107c00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728107c00 p_off=168852480 size=131072 end_off=168983552 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728c6ac00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728c6ac00 p_off=180792320 size=131072 end_off=180923392 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012fd0 buffer=0x7f27b94d3ab0 data(host)=0xc000aca000 dst0=0x7f2728e2ac00 dst1=0x7f2728ecac00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728ecac00 p_off=183282688 size=131072 end_off=183413760 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f2728407c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728407c00 p_off=171998208 size=131072 end_off=172129280 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f2728847c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728847c00 p_off=176454656 size=131072 end_off=176585728 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fa60000 off=27656192 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2728127c00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728127c00 p_off=168983552 size=131072 end_off=169114624 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fa60000 p_off=27656192 size=131072 end_off=27787264 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f2728427c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728427c00 p_off=172129280 size=131072 end_off=172260352 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f2728867c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728867c00 p_off=176585728 size=131072 end_off=176716800 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728c8ac00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728c8ac00 p_off=180923392 size=131072 end_off=181054464 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2728147c00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728147c00 p_off=169114624 size=131072 end_off=169245696 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f2728447c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728447c00 p_off=172260352 size=131072 end_off=172391424 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fa80000 off=27787264 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fa80000 p_off=27787264 size=131072 end_off=27918336 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f2728887c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728887c00 p_off=176716800 size=131072 end_off=176847872 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728caac00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728caac00 p_off=181054464 size=131072 end_off=181185536 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2728167c00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728167c00 p_off=169245696 size=131072 end_off=169376768 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f2728467c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728467c00 p_off=172391424 size=131072 end_off=172522496 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012fd0 buffer=0x7f27b94d3ab0 data(host)=0xc000aca000 dst0=0x7f2728e2ac00 dst1=0x7f2728eeac00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728eeac00 p_off=183413760 size=131072 end_off=183544832 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f27288a7c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27288a7c00 p_off=176847872 size=131072 end_off=176978944 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271faa0000 off=27918336 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f2728187c00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728187c00 p_off=169376768 size=131072 end_off=169507840 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271faa0000 p_off=27918336 size=131072 end_off=28049408 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f2728487c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728487c00 p_off=172522496 size=131072 end_off=172653568 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012fd0 buffer=0x7f27b94d3ab0 data(host)=0xc000aca000 dst0=0x7f2728e2ac00 dst1=0x7f2728f0ac00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728f0ac00 p_off=183544832 size=131072 end_off=183675904 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012450 buffer=0x7f27b94d3ab0 data(host)=0xc00094a000 dst0=0x7f2727d47c00 dst1=0x7f27281a7c00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27281a7c00 p_off=169507840 size=131072 end_off=169638912 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f27288c7c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27288c7c00 p_off=176978944 size=131072 end_off=177110016 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012fd0 buffer=0x7f27b94d3ab0 data(host)=0xc000aca000 dst0=0x7f2728e2ac00 dst1=0x7f2728f2ac00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728f2ac00 p_off=183675904 size=131072 end_off=183806976 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f27284a7c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27284a7c00 p_off=172653568 size=131072 end_off=172784640 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fac0000 off=28049408 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fac0000 p_off=28049408 size=131072 end_off=28180480 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f27288e7c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27288e7c00 p_off=177110016 size=131072 end_off=177241088 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728ccac00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728ccac00 p_off=181185536 size=131072 end_off=181316608 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f27284c7c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27284c7c00 p_off=172784640 size=131072 end_off=172915712 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f2728907c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728907c00 p_off=177241088 size=131072 end_off=177372160 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f27284e7c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27284e7c00 p_off=172915712 size=131072 end_off=173046784 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728ceac00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728ceac00 p_off=181316608 size=131072 end_off=181447680 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f2728f4ac00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728f4ac00 p_off=183806976 size=131072 end_off=183938048 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f2728927c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728927c00 p_off=177372160 size=131072 end_off=177503232 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f2728507c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728507c00 p_off=173046784 size=131072 end_off=173177856 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f2728f6ac00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728f6ac00 p_off=183938048 size=131072 end_off=184069120 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728d0ac00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728d0ac00 p_off=181447680 size=131072 end_off=181578752 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f2728947c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728947c00 p_off=177503232 size=131072 end_off=177634304 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f2728f8ac00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728f8ac00 p_off=184069120 size=131072 end_off=184200192 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fae0000 off=28180480 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fae0000 p_off=28180480 size=131072 end_off=28311552 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f27293cac00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27293cac00 p_off=188525568 size=131072 end_off=188656640 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728d2ac00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728d2ac00 p_off=181578752 size=131072 end_off=181709824 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f2728967c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728967c00 p_off=177634304 size=131072 end_off=177765376 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f2728faac00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728faac00 p_off=184200192 size=131072 end_off=184331264 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f27293eac00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27293eac00 p_off=188656640 size=131072 end_off=188787712 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fb00000 off=28311552 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fb00000 p_off=28311552 size=131072 end_off=28442624 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f2728987c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728987c00 p_off=177765376 size=131072 end_off=177896448 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f2728fcac00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728fcac00 p_off=184331264 size=131072 end_off=184462336 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f272940ac00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272940ac00 p_off=188787712 size=131072 end_off=188918784 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f2728527c00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728527c00 p_off=173177856 size=131072 end_off=173308928 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f27289a7c00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27289a7c00 p_off=177896448 size=131072 end_off=178027520 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fb20000 off=28442624 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fb20000 p_off=28442624 size=131072 end_off=28573696 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f2728feac00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728feac00 p_off=184462336 size=131072 end_off=184593408 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f272942ac00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272942ac00 p_off=188918784 size=131072 end_off=189049856 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f2728547c00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728547c00 p_off=173308928 size=131072 end_off=173440000 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f27289c7c00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27289c7c00 p_off=178027520 size=131072 end_off=178158592 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f272944ac00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272944ac00 p_off=189049856 size=131072 end_off=189180928 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f272900ac00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272900ac00 p_off=184593408 size=131072 end_off=184724480 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fb40000 off=28573696 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fb40000 p_off=28573696 size=131072 end_off=28704768 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f2728567c00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728567c00 p_off=173440000 size=131072 end_off=173571072 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f27289e7c00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27289e7c00 p_off=178158592 size=131072 end_off=178289664 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f272946ac00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272946ac00 p_off=189180928 size=131072 end_off=189312000 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728d4ac00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728d4ac00 p_off=181709824 size=131072 end_off=181840896 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f272902ac00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272902ac00 p_off=184724480 size=131072 end_off=184855552 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f272948ac00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272948ac00 p_off=189312000 size=131072 end_off=189443072 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fb60000 off=28704768 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fb60000 p_off=28704768 size=131072 end_off=28835840 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728d6ac00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728d6ac00 p_off=181840896 size=131072 end_off=181971968 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f272904ac00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272904ac00 p_off=184855552 size=131072 end_off=184986624 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f27294aac00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27294aac00 p_off=189443072 size=131072 end_off=189574144 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728d8ac00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728d8ac00 p_off=181971968 size=131072 end_off=182103040 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f2728a07c00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728a07c00 p_off=178289664 size=131072 end_off=178420736 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f27294cac00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27294cac00 p_off=189574144 size=131072 end_off=189705216 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728daac00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728daac00 p_off=182103040 size=131072 end_off=182234112 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f272906ac00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f2728a27c00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728a27c00 p_off=178420736 size=131072 end_off=178551808 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f27294eac00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27294eac00 p_off=189705216 size=131072 end_off=189836288 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728dcac00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272906ac00 p_off=184986624 size=131072 end_off=185117696 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f2728a47c00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728a47c00 p_off=178551808 size=131072 end_off=178682880 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fb80000 off=28835840 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fb80000 p_off=28835840 size=131072 end_off=28966912 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f272950ac00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272950ac00 p_off=189836288 size=131072 end_off=189967360 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f2728587c00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728587c00 p_off=173571072 size=131072 end_off=173702144 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f272908ac00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272908ac00 p_off=185117696 size=131072 end_off=185248768 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f272952ac00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f27285a7c00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fba0000 off=28966912 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27285a7c00 p_off=173702144 size=131072 end_off=173833216 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fba0000 p_off=28966912 size=131072 end_off=29097984 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272952ac00 p_off=189967360 size=131072 end_off=190098432 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728dcac00 p_off=182234112 size=131072 end_off=182365184 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f2728a67c00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728a67c00 p_off=178682880 size=131072 end_off=178813952 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f272954ac00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272954ac00 p_off=190098432 size=131072 end_off=190229504 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f27290aac00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27290aac00 p_off=185248768 size=131072 end_off=185379840 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fbc0000 off=29097984 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f27285c7c00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27285c7c00 p_off=173833216 size=131072 end_off=173964288 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fbc0000 p_off=29097984 size=131072 end_off=29229056 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728deac00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728deac00 p_off=182365184 size=131072 end_off=182496256 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f272956ac00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272956ac00 p_off=190229504 size=131072 end_off=190360576 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f27290cac00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012e60 buffer=0x7f27b94d3ab0 data(host)=0xc000aaa000 dst0=0x7f2728acac00 dst1=0x7f2728e0ac00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f27285e7c00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27285e7c00 p_off=173964288 size=131072 end_off=174095360 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27290cac00 p_off=185379840 size=131072 end_off=185510912 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fbe0000 off=29229056 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fbe0000 p_off=29229056 size=131072 end_off=29360128 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f272958ac00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272958ac00 p_off=190360576 size=131072 end_off=190491648 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f2728a87c00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728a87c00 p_off=178813952 size=131072 end_off=178945024 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f2728607c00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728607c00 p_off=174095360 size=131072 end_off=174226432 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f27290eac00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27290eac00 p_off=185510912 size=131072 end_off=185641984 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8012730 buffer=0x7f27b94d3ab0 data(host)=0xc0009aa000 dst0=0x7f2728647c00 dst1=0x7f2728aa7c00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728aa7c00 p_off=178945024 size=131072 end_off=179076096 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728e0ac00 p_off=182496256 size=131072 end_off=182627328 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fc00000 off=29360128 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fc00000 p_off=29360128 size=131072 end_off=29491200 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f27295aac00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27295aac00 p_off=190491648 size=131072 end_off=190622720 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80125c0 buffer=0x7f27b94d3ab0 data(host)=0xc00098a000 dst0=0x7f27281c7c00 dst1=0x7f2728627c00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2728627c00 p_off=174226432 size=131072 end_off=174357504 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f272910ac00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272910ac00 p_off=185641984 size=131072 end_off=185773056 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fc20000 off=29491200 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fc20000 p_off=29491200 size=131072 end_off=29622272 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f27295cac00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27295cac00 p_off=190622720 size=131072 end_off=190753792 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f272984ac00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272984ac00 p_off=193244160 size=131072 end_off=193375232 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f27295eac00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27295eac00 p_off=190753792 size=131072 end_off=190884864 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013590 buffer=0x7f27b94d3ab0 data(host)=0xc000700000 dst0=0x7f2729ccac00 dst1=0x7f2729ccac00 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fc40000 off=29622272 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fc40000 p_off=29622272 size=131072 end_off=29753344 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729ccac00 p_off=197962752 size=3072 end_off=197965824 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f272912ac00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272912ac00 p_off=185773056 size=131072 end_off=185904128 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f272986ac00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272986ac00 p_off=193375232 size=131072 end_off=193506304 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f272960ac00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013700 buffer=0x7f27b94d3ab0 data(host)=0xc000720000 dst0=0x7f2729ccb800 dst1=0x7f2729ccb800 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729ccb800 p_off=197965824 size=3072 end_off=197968896 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272960ac00 p_off=190884864 size=131072 end_off=191015936 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fc60000 off=29753344 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fc60000 p_off=29753344 size=131072 end_off=29884416 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013870 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f2729ccc400 dst1=0x7f2729ccc400 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f272914ac00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272914ac00 p_off=185904128 size=131072 end_off=186035200 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729ccc400 p_off=197968896 size=3072 end_off=197971968 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f272962ac00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272962ac00 p_off=191015936 size=131072 end_off=191147008 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80139e0 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f2729ccd000 dst1=0x7f2729ccd000 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729ccd000 p_off=197971968 size=3072 end_off=197975040 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f272916ac00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272916ac00 p_off=186035200 size=131072 end_off=186166272 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fc80000 off=29884416 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fc80000 p_off=29884416 size=131072 end_off=30015488 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f272964ac00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272964ac00 p_off=191147008 size=131072 end_off=191278080 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729ccdc00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729ccdc00 p_off=197975040 size=131072 end_off=198106112 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f272918ac00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272918ac00 p_off=186166272 size=131072 end_off=186297344 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f272966ac00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013cc0 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272a02dc00 dst1=0x7f272a02dc00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a02dc00 p_off=201513984 size=131072 end_off=201645056 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272966ac00 p_off=191278080 size=131072 end_off=191409152 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729cedc00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729cedc00 p_off=198106112 size=131072 end_off=198237184 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fca0000 off=30015488 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fca0000 p_off=30015488 size=131072 end_off=30146560 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f27291aac00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27291aac00 p_off=186297344 size=131072 end_off=186428416 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013cc0 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272a02dc00 dst1=0x7f272a04dc00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a04dc00 p_off=201645056 size=131072 end_off=201776128 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f272968ac00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272968ac00 p_off=191409152 size=131072 end_off=191540224 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729d0dc00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729d0dc00 p_off=198237184 size=131072 end_off=198368256 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f272988ac00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272988ac00 p_off=193506304 size=131072 end_off=193637376 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f27291cac00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27291cac00 p_off=186428416 size=131072 end_off=186559488 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729d2dc00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729d2dc00 p_off=198368256 size=131072 end_off=198499328 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f27296aac00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27296aac00 p_off=191540224 size=131072 end_off=191671296 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013cc0 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272a02dc00 dst1=0x7f272a06dc00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a06dc00 p_off=201776128 size=131072 end_off=201907200 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fcc0000 off=30146560 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fcc0000 p_off=30146560 size=131072 end_off=30277632 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f27298aac00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27298aac00 p_off=193637376 size=131072 end_off=193768448 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729d4dc00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729d4dc00 p_off=198499328 size=131072 end_off=198630400 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f27291eac00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27291eac00 p_off=186559488 size=131072 end_off=186690560 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f27296cac00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27296cac00 p_off=191671296 size=131072 end_off=191802368 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fce0000 off=30277632 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fce0000 p_off=30277632 size=131072 end_off=30408704 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f27298cac00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27298cac00 p_off=193768448 size=131072 end_off=193899520 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729d6dc00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729d6dc00 p_off=198630400 size=131072 end_off=198761472 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f272920ac00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272920ac00 p_off=186690560 size=131072 end_off=186821632 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f27296eac00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27296eac00 p_off=191802368 size=131072 end_off=191933440 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f27298eac00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27298eac00 p_off=193899520 size=131072 end_off=194030592 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f272922ac00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272922ac00 p_off=186821632 size=131072 end_off=186952704 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013cc0 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272a02dc00 dst1=0x7f272a08dc00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a08dc00 p_off=201907200 size=131072 end_off=202038272 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729d8dc00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729d8dc00 p_off=198761472 size=131072 end_off=198892544 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f272970ac00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272970ac00 p_off=191933440 size=131072 end_off=192064512 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f272990ac00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272990ac00 p_off=194030592 size=131072 end_off=194161664 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729dadc00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729dadc00 p_off=198892544 size=131072 end_off=199023616 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f272972ac00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272972ac00 p_off=192064512 size=131072 end_off=192195584 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f272992ac00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272992ac00 p_off=194161664 size=131072 end_off=194292736 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fd00000 off=30408704 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fd00000 p_off=30408704 size=131072 end_off=30539776 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f272924ac00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272924ac00 p_off=186952704 size=131072 end_off=187083776 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729dcdc00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729dcdc00 p_off=199023616 size=131072 end_off=199154688 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f272994ac00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272994ac00 p_off=194292736 size=131072 end_off=194423808 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fd20000 off=30539776 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fd20000 p_off=30539776 size=131072 end_off=30670848 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f272974ac00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272974ac00 p_off=192195584 size=131072 end_off=192326656 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729dedc00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729dedc00 p_off=199154688 size=131072 end_off=199285760 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f272996ac00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272996ac00 p_off=194423808 size=131072 end_off=194554880 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013cc0 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272a02dc00 dst1=0x7f272a0adc00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a0adc00 p_off=202038272 size=131072 end_off=202169344 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f272998ac00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272998ac00 p_off=194554880 size=131072 end_off=194685952 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fd40000 off=30670848 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fd40000 p_off=30670848 size=131072 end_off=30801920 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f272976ac00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272976ac00 p_off=192326656 size=131072 end_off=192457728 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f272926ac00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272926ac00 p_off=187083776 size=131072 end_off=187214848 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729e0dc00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729e0dc00 p_off=199285760 size=131072 end_off=199416832 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013cc0 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272a02dc00 dst1=0x7f272a0cdc00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a0cdc00 p_off=202169344 size=131072 end_off=202300416 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f272928ac00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272928ac00 p_off=187214848 size=131072 end_off=187345920 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fd60000 off=30801920 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fd60000 p_off=30801920 size=131072 end_off=30932992 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f27299aac00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27299aac00 p_off=194685952 size=131072 end_off=194817024 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f272978ac00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272978ac00 p_off=192457728 size=131072 end_off=192588800 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729e2dc00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729e2dc00 p_off=199416832 size=131072 end_off=199547904 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f27292aac00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27292aac00 p_off=187345920 size=131072 end_off=187476992 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f27297aac00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27297aac00 p_off=192588800 size=131072 end_off=192719872 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729e4dc00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729e4dc00 p_off=199547904 size=131072 end_off=199678976 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f27299cac00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27299cac00 p_off=194817024 size=131072 end_off=194948096 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f27292cac00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27292cac00 p_off=187476992 size=131072 end_off=187608064 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f27297cac00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27297cac00 p_off=192719872 size=131072 end_off=192850944 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729e6dc00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729e6dc00 p_off=199678976 size=131072 end_off=199810048 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f27292eac00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27292eac00 p_off=187608064 size=131072 end_off=187739136 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f27297eac00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27297eac00 p_off=192850944 size=131072 end_off=192982016 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f27299eac00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27299eac00 p_off=194948096 size=131072 end_off=195079168 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729e8dc00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729e8dc00 p_off=199810048 size=131072 end_off=199941120 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f272930ac00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272930ac00 p_off=187739136 size=131072 end_off=187870208 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f272980ac00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272980ac00 p_off=192982016 size=131072 end_off=193113088 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80132b0 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f27293cac00 dst1=0x7f272982ac00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272982ac00 p_off=193113088 size=131072 end_off=193244160 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f2729a0ac00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729a0ac00 p_off=195079168 size=131072 end_off=195210240 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013cc0 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272a02dc00 dst1=0x7f272a0edc00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a0edc00 p_off=202300416 size=131072 end_off=202431488 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f2729a2ac00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729a2ac00 p_off=195210240 size=131072 end_off=195341312 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013cc0 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272a02dc00 dst1=0x7f272a10dc00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a10dc00 p_off=202431488 size=131072 end_off=202562560 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a14dc00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a14dc00 p_off=202693632 size=131072 end_off=202824704 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013cc0 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272a02dc00 dst1=0x7f272a12dc00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a12dc00 p_off=202562560 size=131072 end_off=202693632 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f2729a4ac00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729a4ac00 p_off=195341312 size=131072 end_off=195472384 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a16dc00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a16dc00 p_off=202824704 size=131072 end_off=202955776 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f2729a6ac00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729a6ac00 p_off=195472384 size=131072 end_off=195603456 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a18dc00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a18dc00 p_off=202955776 size=131072 end_off=203086848 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fd80000 off=30932992 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fd80000 p_off=30932992 size=131072 end_off=31064064 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f2729a8ac00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729a8ac00 p_off=195603456 size=131072 end_off=195734528 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a1adc00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a1adc00 p_off=203086848 size=131072 end_off=203217920 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fda0000 off=31064064 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fda0000 p_off=31064064 size=131072 end_off=31195136 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729eadc00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729eadc00 p_off=199941120 size=131072 end_off=200072192 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f2729aaac00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729aaac00 p_off=195734528 size=131072 end_off=195865600 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a1cdc00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a1cdc00 p_off=203217920 size=131072 end_off=203348992 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fdc0000 off=31195136 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fdc0000 p_off=31195136 size=131072 end_off=31326208 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729ecdc00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729ecdc00 p_off=200072192 size=131072 end_off=200203264 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a1edc00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a1edc00 p_off=203348992 size=131072 end_off=203480064 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f2729acac00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729acac00 p_off=195865600 size=131072 end_off=195996672 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fde0000 off=31326208 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fde0000 p_off=31326208 size=131072 end_off=31457280 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f272932ac00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a20dc00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a20dc00 p_off=203480064 size=131072 end_off=203611136 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272932ac00 p_off=187870208 size=131072 end_off=188001280 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f2729aeac00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729aeac00 p_off=195996672 size=131072 end_off=196127744 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fe00000 off=31457280 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fe00000 p_off=31457280 size=131072 end_off=31588352 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a5cdc00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a5cdc00 p_off=207412224 size=131072 end_off=207543296 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a22dc00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a22dc00 p_off=203611136 size=131072 end_off=203742208 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f272934ac00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729eedc00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fe20000 off=31588352 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a5edc00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a5edc00 p_off=207543296 size=131072 end_off=207674368 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272934ac00 p_off=188001280 size=131072 end_off=188132352 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fe20000 p_off=31588352 size=131072 end_off=31719424 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a24dc00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a24dc00 p_off=203742208 size=131072 end_off=203873280 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f2729b0ac00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729b0ac00 p_off=196127744 size=131072 end_off=196258816 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a60dc00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a60dc00 p_off=207674368 size=131072 end_off=207805440 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f272936ac00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272936ac00 p_off=188132352 size=131072 end_off=188263424 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a26dc00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729eedc00 p_off=200203264 size=131072 end_off=200334336 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fe40000 off=31719424 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f272938ac00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a26dc00 p_off=203873280 size=131072 end_off=204004352 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272938ac00 p_off=188263424 size=131072 end_off=188394496 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fe40000 p_off=31719424 size=131072 end_off=31850496 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f2729b2ac00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729b2ac00 p_off=196258816 size=131072 end_off=196389888 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013140 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f2728f4ac00 dst1=0x7f27293aac00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27293aac00 p_off=188394496 size=131072 end_off=188525568 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729f0dc00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729f0dc00 p_off=200334336 size=131072 end_off=200465408 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a62dc00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a62dc00 p_off=207805440 size=131072 end_off=207936512 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fe60000 off=31850496 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fe60000 p_off=31850496 size=131072 end_off=31981568 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f2729b4ac00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729b4ac00 p_off=196389888 size=131072 end_off=196520960 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a28dc00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a28dc00 p_off=204004352 size=131072 end_off=204135424 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a64dc00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a64dc00 p_off=207936512 size=131072 end_off=208067584 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fe80000 off=31981568 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fe80000 p_off=31981568 size=131072 end_off=32112640 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272aa4dc00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272aa4dc00 p_off=212130816 size=131072 end_off=212261888 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f2729b6ac00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729b6ac00 p_off=196520960 size=131072 end_off=196652032 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729f2dc00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729f2dc00 p_off=200465408 size=131072 end_off=200596480 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fea0000 off=32112640 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fea0000 p_off=32112640 size=131072 end_off=32243712 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272aa6dc00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272aa6dc00 p_off=212261888 size=131072 end_off=212392960 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a2adc00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a2adc00 p_off=204135424 size=131072 end_off=204266496 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f2729b8ac00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729b8ac00 p_off=196652032 size=131072 end_off=196783104 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fec0000 off=32243712 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fec0000 p_off=32243712 size=131072 end_off=32374784 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a66dc00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a66dc00 p_off=208067584 size=131072 end_off=208198656 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729f4dc00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729f4dc00 p_off=200596480 size=131072 end_off=200727552 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272aa8dc00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272aa8dc00 p_off=212392960 size=131072 end_off=212524032 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f2729baac00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729baac00 p_off=196783104 size=131072 end_off=196914176 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a2cdc00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a2cdc00 p_off=204266496 size=131072 end_off=204397568 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a68dc00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a68dc00 p_off=208198656 size=131072 end_off=208329728 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271fee0000 off=32374784 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271fee0000 p_off=32374784 size=131072 end_off=32505856 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272aaadc00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272aaadc00 p_off=212524032 size=131072 end_off=212655104 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f2729bcac00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729bcac00 p_off=196914176 size=131072 end_off=197045248 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a6adc00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a6adc00 p_off=208329728 size=131072 end_off=208460800 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a2edc00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a2edc00 p_off=204397568 size=131072 end_off=204528640 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729f6dc00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729f6dc00 p_off=200727552 size=131072 end_off=200858624 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ff00000 off=32505856 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ff00000 p_off=32505856 size=131072 end_off=32636928 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f2729beac00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729beac00 p_off=197045248 size=131072 end_off=197176320 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a6cdc00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a6cdc00 p_off=208460800 size=131072 end_off=208591872 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a30dc00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a30dc00 p_off=204528640 size=131072 end_off=204659712 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729f8dc00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729f8dc00 p_off=200858624 size=131072 end_off=200989696 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f2729c0ac00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729c0ac00 p_off=197176320 size=131072 end_off=197307392 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a6edc00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ff20000 off=32636928 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ff20000 p_off=32636928 size=131072 end_off=32768000 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729fadc00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729fadc00 p_off=200989696 size=131072 end_off=201120768 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f2729c2ac00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729c2ac00 p_off=197307392 size=131072 end_off=197438464 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a32dc00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a32dc00 p_off=204659712 size=131072 end_off=204790784 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729fcdc00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a6edc00 p_off=208591872 size=131072 end_off=208722944 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729fcdc00 p_off=201120768 size=131072 end_off=201251840 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f2729c4ac00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729c4ac00 p_off=197438464 size=131072 end_off=197569536 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272aacdc00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272aacdc00 p_off=212655104 size=131072 end_off=212786176 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a34dc00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a34dc00 p_off=204790784 size=131072 end_off=204921856 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a70dc00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a70dc00 p_off=208722944 size=131072 end_off=208854016 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f2729c6ac00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729c6ac00 p_off=197569536 size=131072 end_off=197700608 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272aaedc00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272aaedc00 p_off=212786176 size=131072 end_off=212917248 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a36dc00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a36dc00 p_off=204921856 size=131072 end_off=205052928 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a72dc00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ff40000 off=32768000 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ff40000 p_off=32768000 size=131072 end_off=32899072 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a72dc00 p_off=208854016 size=131072 end_off=208985088 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f2729c8ac00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729c8ac00 p_off=197700608 size=131072 end_off=197831680 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f2729fedc00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729fedc00 p_off=201251840 size=131072 end_off=201382912 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a38dc00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a38dc00 p_off=205052928 size=131072 end_off=205184000 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013b50 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f2729ccdc00 dst1=0x7f272a00dc00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a00dc00 p_off=201382912 size=131072 end_off=201513984 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a74dc00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a74dc00 p_off=208985088 size=131072 end_off=209116160 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a3adc00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a3adc00 p_off=205184000 size=131072 end_off=205315072 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013420 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272984ac00 dst1=0x7f2729caac00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2729caac00 p_off=197831680 size=131072 end_off=197962752 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014280 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f272aecdc00 dst1=0x7f272aecdc00 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272aecdc00 p_off=216849408 size=3072 end_off=216852480 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a76dc00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a76dc00 p_off=209116160 size=131072 end_off=209247232 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ff60000 off=32899072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ff60000 p_off=32899072 size=131072 end_off=33030144 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80143f0 buffer=0x7f27b94d3ab0 data(host)=0xc0008ca000 dst0=0x7f272aece800 dst1=0x7f272aece800 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272aece800 p_off=216852480 size=3072 end_off=216855552 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a3cdc00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a3cdc00 p_off=205315072 size=131072 end_off=205446144 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014560 buffer=0x7f27b94d3ab0 data(host)=0xc0008ea000 dst0=0x7f272aecf400 dst1=0x7f272aecf400 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272aecf400 p_off=216855552 size=3072 end_off=216858624 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80146d0 buffer=0x7f27b94d3ab0 data(host)=0xc00090a000 dst0=0x7f272aed0000 dst1=0x7f272aed0000 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272aed0000 p_off=216858624 size=3072 end_off=216861696 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a78dc00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a78dc00 p_off=209247232 size=131072 end_off=209378304 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272ab0dc00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ab0dc00 p_off=212917248 size=131072 end_off=213048320 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a3edc00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a3edc00 p_off=205446144 size=131072 end_off=205577216 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272aed0c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272aed0c00 p_off=216861696 size=131072 end_off=216992768 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a7adc00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a7adc00 p_off=209378304 size=131072 end_off=209509376 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272ab2dc00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ab2dc00 p_off=213048320 size=131072 end_off=213179392 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80149b0 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f272b230c00 dst1=0x7f272b230c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b230c00 p_off=220400640 size=131072 end_off=220531712 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a40dc00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a40dc00 p_off=205577216 size=131072 end_off=205708288 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a7cdc00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a7cdc00 p_off=209509376 size=131072 end_off=209640448 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272ab4dc00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ab4dc00 p_off=213179392 size=131072 end_off=213310464 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ff80000 off=33030144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ff80000 p_off=33030144 size=131072 end_off=33161216 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a7edc00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a7edc00 p_off=209640448 size=131072 end_off=209771520 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272ab6dc00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ab6dc00 p_off=213310464 size=131072 end_off=213441536 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272aef0c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272aef0c00 p_off=216992768 size=131072 end_off=217123840 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80149b0 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f272b230c00 dst1=0x7f272b250c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a42dc00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a42dc00 p_off=205708288 size=131072 end_off=205839360 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b250c00 p_off=220531712 size=131072 end_off=220662784 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a80dc00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a80dc00 p_off=209771520 size=131072 end_off=209902592 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272ab8dc00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ab8dc00 p_off=213441536 size=131072 end_off=213572608 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ffa0000 off=33161216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ffa0000 p_off=33161216 size=131072 end_off=33292288 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272af10c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272af10c00 p_off=217123840 size=131072 end_off=217254912 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272abadc00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272abadc00 p_off=213572608 size=131072 end_off=213703680 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ffc0000 off=33292288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ffc0000 p_off=33292288 size=131072 end_off=33423360 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a82dc00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a82dc00 p_off=209902592 size=131072 end_off=210033664 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272abcdc00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272abcdc00 p_off=213703680 size=131072 end_off=213834752 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a44dc00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a44dc00 p_off=205839360 size=131072 end_off=205970432 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80149b0 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f272b230c00 dst1=0x7f272b270c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b270c00 p_off=220662784 size=131072 end_off=220793856 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272af30c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272af30c00 p_off=217254912 size=131072 end_off=217385984 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f271ffe0000 off=33423360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f271ffe0000 p_off=33423360 size=131072 end_off=33554432 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a84dc00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a84dc00 p_off=210033664 size=131072 end_off=210164736 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272abedc00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272abedc00 p_off=213834752 size=131072 end_off=213965824 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80149b0 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f272b230c00 dst1=0x7f272b290c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b290c00 p_off=220793856 size=131072 end_off=220924928 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272af50c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272af50c00 p_off=217385984 size=131072 end_off=217517056 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a86dc00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a86dc00 p_off=210164736 size=131072 end_off=210295808 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720000000 off=33554432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720000000 p_off=33554432 size=131072 end_off=33685504 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272ac0dc00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ac0dc00 p_off=213965824 size=131072 end_off=214096896 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80149b0 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f272b230c00 dst1=0x7f272b2b0c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b2b0c00 p_off=220924928 size=131072 end_off=221056000 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272af70c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272af70c00 p_off=217517056 size=131072 end_off=217648128 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a46dc00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a46dc00 p_off=205970432 size=131072 end_off=206101504 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a88dc00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a88dc00 p_off=210295808 size=131072 end_off=210426880 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720020000 off=33685504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720020000 p_off=33685504 size=131072 end_off=33816576 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272ac2dc00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ac2dc00 p_off=214096896 size=131072 end_off=214227968 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80149b0 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f272b230c00 dst1=0x7f272b2d0c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b2d0c00 p_off=221056000 size=131072 end_off=221187072 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a48dc00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a48dc00 p_off=206101504 size=131072 end_off=206232576 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a8adc00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a8adc00 p_off=210426880 size=131072 end_off=210557952 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272ac4dc00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ac4dc00 p_off=214227968 size=131072 end_off=214359040 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720040000 off=33816576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80149b0 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f272b230c00 dst1=0x7f272b2f0c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b2f0c00 p_off=221187072 size=131072 end_off=221318144 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720040000 p_off=33816576 size=131072 end_off=33947648 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a4adc00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a4adc00 p_off=206232576 size=131072 end_off=206363648 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a8cdc00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a8cdc00 p_off=210557952 size=131072 end_off=210689024 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272af90c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272af90c00 p_off=217648128 size=131072 end_off=217779200 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272ac6dc00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ac6dc00 p_off=214359040 size=131072 end_off=214490112 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80149b0 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f272b230c00 dst1=0x7f272b310c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b310c00 p_off=221318144 size=131072 end_off=221449216 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a8edc00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a8edc00 p_off=210689024 size=131072 end_off=210820096 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272afb0c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272afb0c00 p_off=217779200 size=131072 end_off=217910272 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272ac8dc00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ac8dc00 p_off=214490112 size=131072 end_off=214621184 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a90dc00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a90dc00 p_off=210820096 size=131072 end_off=210951168 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80149b0 buffer=0x7f27b94d3ab0 data(host)=0xc00096a000 dst0=0x7f272b230c00 dst1=0x7f272b330c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b330c00 p_off=221449216 size=131072 end_off=221580288 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272afd0c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272afd0c00 p_off=217910272 size=131072 end_off=218041344 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272acadc00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272acadc00 p_off=214621184 size=131072 end_off=214752256 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720060000 off=33947648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720060000 p_off=33947648 size=131072 end_off=34078720 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a92dc00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a92dc00 p_off=210951168 size=131072 end_off=211082240 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a4cdc00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a4cdc00 p_off=206363648 size=131072 end_off=206494720 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272accdc00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272accdc00 p_off=214752256 size=131072 end_off=214883328 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a94dc00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a94dc00 p_off=211082240 size=131072 end_off=211213312 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b350c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b350c00 p_off=221580288 size=131072 end_off=221711360 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720080000 off=34078720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720080000 p_off=34078720 size=131072 end_off=34209792 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a4edc00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a4edc00 p_off=206494720 size=131072 end_off=206625792 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272acedc00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272acedc00 p_off=214883328 size=131072 end_off=215014400 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a96dc00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a96dc00 p_off=211213312 size=131072 end_off=211344384 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b370c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b370c00 p_off=221711360 size=131072 end_off=221842432 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272aff0c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272aff0c00 p_off=218041344 size=131072 end_off=218172416 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272ad0dc00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ad0dc00 p_off=215014400 size=131072 end_off=215145472 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a50dc00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a50dc00 p_off=206625792 size=131072 end_off=206756864 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b390c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b390c00 p_off=221842432 size=131072 end_off=221973504 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272b010c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b010c00 p_off=218172416 size=131072 end_off=218303488 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27200a0000 off=34209792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27200a0000 p_off=34209792 size=131072 end_off=34340864 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272b030c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b030c00 p_off=218303488 size=131072 end_off=218434560 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b3b0c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b3b0c00 p_off=221973504 size=131072 end_off=222104576 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a98dc00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a98dc00 p_off=211344384 size=131072 end_off=211475456 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272ad2dc00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ad2dc00 p_off=215145472 size=131072 end_off=215276544 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27200c0000 off=34340864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27200c0000 p_off=34340864 size=131072 end_off=34471936 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a52dc00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a52dc00 p_off=206756864 size=131072 end_off=206887936 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272b050c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b050c00 p_off=218434560 size=131072 end_off=218565632 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a9adc00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a9adc00 p_off=211475456 size=131072 end_off=211606528 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b3d0c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b3d0c00 p_off=222104576 size=131072 end_off=222235648 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272ad4dc00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ad4dc00 p_off=215276544 size=131072 end_off=215407616 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272b070c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b070c00 p_off=218565632 size=131072 end_off=218696704 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a54dc00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a54dc00 p_off=206887936 size=131072 end_off=207019008 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27200e0000 off=34471936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27200e0000 p_off=34471936 size=131072 end_off=34603008 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b3f0c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b3f0c00 p_off=222235648 size=131072 end_off=222366720 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272ad6dc00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ad6dc00 p_off=215407616 size=131072 end_off=215538688 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272b090c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b090c00 p_off=218696704 size=131072 end_off=218827776 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272ad8dc00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ad8dc00 p_off=215538688 size=131072 end_off=215669760 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a9cdc00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a9cdc00 p_off=211606528 size=131072 end_off=211737600 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720100000 off=34603008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720100000 p_off=34603008 size=131072 end_off=34734080 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a56dc00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a56dc00 p_off=207019008 size=131072 end_off=207150080 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b410c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b410c00 p_off=222366720 size=131072 end_off=222497792 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272b0b0c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b0b0c00 p_off=218827776 size=131072 end_off=218958848 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272adadc00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272adadc00 p_off=215669760 size=131072 end_off=215800832 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720120000 off=34734080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720120000 p_off=34734080 size=131072 end_off=34865152 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a58dc00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a58dc00 p_off=207150080 size=131072 end_off=207281152 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272a9edc00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a9edc00 p_off=211737600 size=131072 end_off=211868672 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b430c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b430c00 p_off=222497792 size=131072 end_off=222628864 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272b0d0c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b0d0c00 p_off=218958848 size=131072 end_off=219089920 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272adcdc00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272adcdc00 p_off=215800832 size=131072 end_off=215931904 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720140000 off=34865152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720140000 p_off=34865152 size=131072 end_off=34996224 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013e30 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272a14dc00 dst1=0x7f272a5adc00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272a5adc00 p_off=207281152 size=131072 end_off=207412224 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b450c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b450c00 p_off=222628864 size=131072 end_off=222759936 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272adedc00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272adedc00 p_off=215931904 size=131072 end_off=216062976 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272b0f0c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b0f0c00 p_off=219089920 size=131072 end_off=219220992 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272aa0dc00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272aa0dc00 p_off=211868672 size=131072 end_off=211999744 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720160000 off=34996224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720160000 p_off=34996224 size=131072 end_off=35127296 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b470c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b470c00 p_off=222759936 size=131072 end_off=222891008 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272ae0dc00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ae0dc00 p_off=216062976 size=131072 end_off=216194048 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8013fa0 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272a5cdc00 dst1=0x7f272aa2dc00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272aa2dc00 p_off=211999744 size=131072 end_off=212130816 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272b110c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b110c00 p_off=219220992 size=131072 end_off=219352064 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272ae2dc00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ae2dc00 p_off=216194048 size=131072 end_off=216325120 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272b7d0c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b7d0c00 p_off=226298880 size=131072 end_off=226429952 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272b130c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b130c00 p_off=219352064 size=131072 end_off=219483136 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b490c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b490c00 p_off=222891008 size=131072 end_off=223022080 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272ae4dc00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ae4dc00 p_off=216325120 size=131072 end_off=216456192 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272b7f0c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b7f0c00 p_off=226429952 size=131072 end_off=226561024 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272ae6dc00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ae6dc00 p_off=216456192 size=131072 end_off=216587264 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b4b0c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b4b0c00 p_off=223022080 size=131072 end_off=223153152 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272b150c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b150c00 p_off=219483136 size=131072 end_off=219614208 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272bc50c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bc50c00 p_off=231017472 size=131072 end_off=231148544 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272b810c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b810c00 p_off=226561024 size=131072 end_off=226692096 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272ae8dc00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ae8dc00 p_off=216587264 size=131072 end_off=216718336 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b4d0c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b4d0c00 p_off=223153152 size=131072 end_off=223284224 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014110 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272aa4dc00 dst1=0x7f272aeadc00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272aeadc00 p_off=216718336 size=131072 end_off=216849408 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272b170c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272bc70c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bc70c00 p_off=231148544 size=131072 end_off=231279616 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b170c00 p_off=219614208 size=131072 end_off=219745280 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720180000 off=35127296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720180000 p_off=35127296 size=131072 end_off=35258368 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b4f0c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b4f0c00 p_off=223284224 size=131072 end_off=223415296 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014f70 buffer=0x7f27b94d3ab0 data(host)=0xc000a2a000 dst0=0x7f272c0d0c00 dst1=0x7f272c0d0c00 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c0d0c00 p_off=235736064 size=3072 end_off=235739136 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272bc90c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bc90c00 p_off=231279616 size=131072 end_off=231410688 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27201a0000 off=35258368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27201a0000 p_off=35258368 size=131072 end_off=35389440 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b510c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b510c00 p_off=223415296 size=131072 end_off=223546368 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80150e0 buffer=0x7f27b94d3ab0 data(host)=0xc000a4a000 dst0=0x7f272c0d1800 dst1=0x7f272c0d1800 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c0d1800 p_off=235739136 size=3072 end_off=235742208 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272bcb0c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bcb0c00 p_off=231410688 size=131072 end_off=231541760 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b530c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b530c00 p_off=223546368 size=131072 end_off=223677440 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272bcd0c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bcd0c00 p_off=231541760 size=131072 end_off=231672832 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27201c0000 off=35389440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27201c0000 p_off=35389440 size=131072 end_off=35520512 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272b190c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b190c00 p_off=219745280 size=131072 end_off=219876352 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015250 buffer=0x7f27b94d3ab0 data(host)=0xc000a6a000 dst0=0x7f272c0d2400 dst1=0x7f272c0d2400 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c0d2400 p_off=235742208 size=3072 end_off=235745280 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272bcf0c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bcf0c00 p_off=231672832 size=131072 end_off=231803904 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27201e0000 off=35520512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27201e0000 p_off=35520512 size=131072 end_off=35651584 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272b1b0c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b1b0c00 p_off=219876352 size=131072 end_off=220007424 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80153c0 buffer=0x7f27b94d3ab0 data(host)=0xc000a8a000 dst0=0x7f272c0d3000 dst1=0x7f272c0d3000 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c0d3000 p_off=235745280 size=3072 end_off=235748352 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272bd10c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bd10c00 p_off=231803904 size=131072 end_off=231934976 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720200000 off=35651584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720200000 p_off=35651584 size=131072 end_off=35782656 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272b1d0c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b1d0c00 p_off=220007424 size=131072 end_off=220138496 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272bd30c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bd30c00 p_off=231934976 size=131072 end_off=232066048 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c0d3c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c0d3c00 p_off=235748352 size=131072 end_off=235879424 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720220000 off=35782656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720220000 p_off=35782656 size=131072 end_off=35913728 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b550c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b550c00 p_off=223677440 size=131072 end_off=223808512 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272b1f0c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b1f0c00 p_off=220138496 size=131072 end_off=220269568 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c0f3c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c0f3c00 p_off=235879424 size=131072 end_off=236010496 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272b830c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b830c00 p_off=226692096 size=131072 end_off=226823168 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272bd50c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bd50c00 p_off=232066048 size=131072 end_off=232197120 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b570c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720240000 off=35913728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720240000 p_off=35913728 size=131072 end_off=36044800 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014840 buffer=0x7f27b94d3ab0 data(host)=0xc00092a000 dst0=0x7f272aed0c00 dst1=0x7f272b210c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b210c00 p_off=220269568 size=131072 end_off=220400640 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c113c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c113c00 p_off=236010496 size=131072 end_off=236141568 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b570c00 p_off=223808512 size=131072 end_off=223939584 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272b850c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b850c00 p_off=226823168 size=131072 end_off=226954240 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720260000 off=36044800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720260000 p_off=36044800 size=131072 end_off=36175872 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c133c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c133c00 p_off=236141568 size=131072 end_off=236272640 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720280000 off=36175872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720280000 p_off=36175872 size=131072 end_off=36306944 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80156a0 buffer=0x7f27b94d3ab0 data(host)=0xc000b0a000 dst0=0x7f272c433c00 dst1=0x7f272c433c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c153c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c153c00 p_off=236272640 size=131072 end_off=236403712 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c433c00 p_off=239287296 size=131072 end_off=239418368 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b590c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b590c00 p_off=223939584 size=131072 end_off=224070656 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272bd70c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bd70c00 p_off=232197120 size=131072 end_off=232328192 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27202a0000 off=36306944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27202a0000 p_off=36306944 size=131072 end_off=36438016 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c173c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c173c00 p_off=236403712 size=131072 end_off=236534784 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80156a0 buffer=0x7f27b94d3ab0 data(host)=0xc000b0a000 dst0=0x7f272c433c00 dst1=0x7f272c453c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c453c00 p_off=239418368 size=131072 end_off=239549440 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b5b0c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b5b0c00 p_off=224070656 size=131072 end_off=224201728 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c193c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c193c00 p_off=236534784 size=131072 end_off=236665856 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272b870c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b870c00 p_off=226954240 size=131072 end_off=227085312 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27202c0000 off=36438016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27202c0000 p_off=36438016 size=131072 end_off=36569088 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272bd90c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bd90c00 p_off=232328192 size=131072 end_off=232459264 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80156a0 buffer=0x7f27b94d3ab0 data(host)=0xc000b0a000 dst0=0x7f272c433c00 dst1=0x7f272c473c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c473c00 p_off=239549440 size=131072 end_off=239680512 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c1b3c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c1b3c00 p_off=236665856 size=131072 end_off=236796928 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272b890c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b890c00 p_off=227085312 size=131072 end_off=227216384 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272bdb0c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bdb0c00 p_off=232459264 size=131072 end_off=232590336 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80156a0 buffer=0x7f27b94d3ab0 data(host)=0xc000b0a000 dst0=0x7f272c433c00 dst1=0x7f272c493c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c493c00 p_off=239680512 size=131072 end_off=239811584 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c1d3c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c1d3c00 p_off=236796928 size=131072 end_off=236928000 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27202e0000 off=36569088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27202e0000 p_off=36569088 size=131072 end_off=36700160 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272bdd0c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bdd0c00 p_off=232590336 size=131072 end_off=232721408 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c1f3c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80156a0 buffer=0x7f27b94d3ab0 data(host)=0xc000b0a000 dst0=0x7f272c433c00 dst1=0x7f272c4b3c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c4b3c00 p_off=239811584 size=131072 end_off=239942656 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c1f3c00 p_off=236928000 size=131072 end_off=237059072 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720300000 off=36700160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720300000 p_off=36700160 size=131072 end_off=36831232 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272b8b0c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b8b0c00 p_off=227216384 size=131072 end_off=227347456 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b5d0c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b5d0c00 p_off=224201728 size=131072 end_off=224332800 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80156a0 buffer=0x7f27b94d3ab0 data(host)=0xc000b0a000 dst0=0x7f272c433c00 dst1=0x7f272c4d3c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c4d3c00 p_off=239942656 size=131072 end_off=240073728 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c213c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c213c00 p_off=237059072 size=131072 end_off=237190144 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720320000 off=36831232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720320000 p_off=36831232 size=131072 end_off=36962304 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c233c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c233c00 p_off=237190144 size=131072 end_off=237321216 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c253c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c253c00 p_off=237321216 size=131072 end_off=237452288 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272b8d0c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b8d0c00 p_off=227347456 size=131072 end_off=227478528 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720340000 off=36962304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720340000 p_off=36962304 size=131072 end_off=37093376 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b5f0c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b5f0c00 p_off=224332800 size=131072 end_off=224463872 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c273c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c273c00 p_off=237452288 size=131072 end_off=237583360 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272bdf0c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bdf0c00 p_off=232721408 size=131072 end_off=232852480 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b610c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b610c00 p_off=224463872 size=131072 end_off=224594944 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80156a0 buffer=0x7f27b94d3ab0 data(host)=0xc000b0a000 dst0=0x7f272c433c00 dst1=0x7f272c4f3c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c4f3c00 p_off=240073728 size=131072 end_off=240204800 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720360000 off=37093376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c293c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c293c00 p_off=237583360 size=131072 end_off=237714432 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720360000 p_off=37093376 size=131072 end_off=37224448 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272b8f0c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b8f0c00 p_off=227478528 size=131072 end_off=227609600 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b630c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b630c00 p_off=224594944 size=131072 end_off=224726016 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80156a0 buffer=0x7f27b94d3ab0 data(host)=0xc000b0a000 dst0=0x7f272c433c00 dst1=0x7f272c513c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c513c00 p_off=240204800 size=131072 end_off=240335872 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c2b3c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c2b3c00 p_off=237714432 size=131072 end_off=237845504 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272be10c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272be10c00 p_off=232852480 size=131072 end_off=232983552 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c2d3c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c2d3c00 p_off=237845504 size=131072 end_off=237976576 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272b910c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b910c00 p_off=227609600 size=131072 end_off=227740672 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c2f3c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c2f3c00 p_off=237976576 size=131072 end_off=238107648 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272be30c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272be30c00 p_off=232983552 size=131072 end_off=233114624 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b650c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b650c00 p_off=224726016 size=131072 end_off=224857088 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80156a0 buffer=0x7f27b94d3ab0 data(host)=0xc000b0a000 dst0=0x7f272c433c00 dst1=0x7f272c533c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c313c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c313c00 p_off=238107648 size=131072 end_off=238238720 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720380000 off=37224448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720380000 p_off=37224448 size=131072 end_off=37355520 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272be50c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272be50c00 p_off=233114624 size=131072 end_off=233245696 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c333c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c333c00 p_off=238238720 size=131072 end_off=238369792 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c533c00 p_off=240335872 size=131072 end_off=240466944 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b670c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b670c00 p_off=224857088 size=131072 end_off=224988160 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272b930c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b930c00 p_off=227740672 size=131072 end_off=227871744 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27203a0000 off=37355520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27203a0000 p_off=37355520 size=131072 end_off=37486592 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b690c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b690c00 p_off=224988160 size=131072 end_off=225119232 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c553c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c553c00 p_off=240466944 size=131072 end_off=240598016 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27203c0000 off=37486592 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27203c0000 p_off=37486592 size=131072 end_off=37617664 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b6b0c00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b6b0c00 p_off=225119232 size=131072 end_off=225250304 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c573c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c573c00 p_off=240598016 size=131072 end_off=240729088 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272b950c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b950c00 p_off=227871744 size=131072 end_off=228002816 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27203e0000 off=37617664 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27203e0000 p_off=37617664 size=131072 end_off=37748736 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b6d0c00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b6d0c00 p_off=225250304 size=131072 end_off=225381376 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272b970c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b970c00 p_off=228002816 size=131072 end_off=228133888 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272be70c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272be70c00 p_off=233245696 size=131072 end_off=233376768 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b6f0c00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b6f0c00 p_off=225381376 size=131072 end_off=225512448 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272b990c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b990c00 p_off=228133888 size=131072 end_off=228264960 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c353c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c353c00 p_off=238369792 size=131072 end_off=238500864 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c593c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c593c00 p_off=240729088 size=131072 end_off=240860160 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c373c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c373c00 p_off=238500864 size=131072 end_off=238631936 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c5b3c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c5b3c00 p_off=240860160 size=131072 end_off=240991232 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c393c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c393c00 p_off=238631936 size=131072 end_off=238763008 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c5d3c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c5d3c00 p_off=240991232 size=131072 end_off=241122304 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c3b3c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c3b3c00 p_off=238763008 size=131072 end_off=238894080 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c5f3c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c5f3c00 p_off=241122304 size=131072 end_off=241253376 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c3d3c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c3d3c00 p_off=238894080 size=131072 end_off=239025152 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c613c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c613c00 p_off=241253376 size=131072 end_off=241384448 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c3f3c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c3f3c00 p_off=239025152 size=131072 end_off=239156224 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015530 buffer=0x7f27b94d3ab0 data(host)=0xc000aea000 dst0=0x7f272c0d3c00 dst1=0x7f272c413c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c413c00 p_off=239156224 size=131072 end_off=239287296 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c633c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c633c00 p_off=241384448 size=131072 end_off=241515520 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c653c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c653c00 p_off=241515520 size=131072 end_off=241646592 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720400000 off=37748736 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720400000 p_off=37748736 size=131072 end_off=37879808 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272c9d3c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c9d3c00 p_off=245185536 size=131072 end_off=245316608 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c673c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c673c00 p_off=241646592 size=131072 end_off=241777664 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720420000 off=37879808 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720420000 p_off=37879808 size=131072 end_off=38010880 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272b9b0c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b9b0c00 p_off=228264960 size=131072 end_off=228396032 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272c9f3c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c9f3c00 p_off=245316608 size=131072 end_off=245447680 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272be90c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272be90c00 p_off=233376768 size=131072 end_off=233507840 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272b9d0c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b9d0c00 p_off=228396032 size=131072 end_off=228527104 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272beb0c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272beb0c00 p_off=233507840 size=131072 end_off=233638912 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272ca13c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ca13c00 p_off=245447680 size=131072 end_off=245578752 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272bed0c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bed0c00 p_off=233638912 size=131072 end_off=233769984 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c693c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c693c00 p_off=241777664 size=131072 end_off=241908736 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272bef0c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bef0c00 p_off=233769984 size=131072 end_off=233901056 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272ca33c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c6b3c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c6b3c00 p_off=241908736 size=131072 end_off=242039808 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272b9f0c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272bf10c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bf10c00 p_off=233901056 size=131072 end_off=234032128 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b9f0c00 p_off=228527104 size=131072 end_off=228658176 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ca33c00 p_off=245578752 size=131072 end_off=245709824 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720440000 off=38010880 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720440000 p_off=38010880 size=131072 end_off=38141952 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c6d3c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c6d3c00 p_off=242039808 size=131072 end_off=242170880 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b710c00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b710c00 p_off=225512448 size=131072 end_off=225643520 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272bf30c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bf30c00 p_off=234032128 size=131072 end_off=234163200 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272ba10c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ba10c00 p_off=228658176 size=131072 end_off=228789248 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b730c00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b730c00 p_off=225643520 size=131072 end_off=225774592 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720460000 off=38141952 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720460000 p_off=38141952 size=131072 end_off=38273024 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c6f3c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c6f3c00 p_off=242170880 size=131072 end_off=242301952 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272ca53c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ca53c00 p_off=245709824 size=131072 end_off=245840896 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272bf50c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bf50c00 p_off=234163200 size=131072 end_off=234294272 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272ba30c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ba30c00 p_off=228789248 size=131072 end_off=228920320 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272bf70c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bf70c00 p_off=234294272 size=131072 end_off=234425344 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720480000 off=38273024 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720480000 p_off=38273024 size=131072 end_off=38404096 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c713c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c713c00 p_off=242301952 size=131072 end_off=242433024 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b750c00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b750c00 p_off=225774592 size=131072 end_off=225905664 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272ca73c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ca73c00 p_off=245840896 size=131072 end_off=245971968 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272ba50c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ba50c00 p_off=228920320 size=131072 end_off=229051392 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272bf90c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bf90c00 p_off=234425344 size=131072 end_off=234556416 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27204a0000 off=38404096 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27204a0000 p_off=38404096 size=131072 end_off=38535168 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b770c00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b770c00 p_off=225905664 size=131072 end_off=226036736 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272ca93c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ca93c00 p_off=245971968 size=131072 end_off=246103040 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272ba70c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ba70c00 p_off=229051392 size=131072 end_off=229182464 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272bfb0c00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bfb0c00 p_off=234556416 size=131072 end_off=234687488 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c733c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c733c00 p_off=242433024 size=131072 end_off=242564096 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272cab3c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cab3c00 p_off=246103040 size=131072 end_off=246234112 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272ba90c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ba90c00 p_off=229182464 size=131072 end_off=229313536 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272cad3c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cad3c00 p_off=246234112 size=131072 end_off=246365184 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b790c00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b790c00 p_off=226036736 size=131072 end_off=226167808 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27204c0000 off=38535168 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27204c0000 p_off=38535168 size=131072 end_off=38666240 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272bfd0c00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bfd0c00 p_off=234687488 size=131072 end_off=234818560 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272bab0c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bab0c00 p_off=229313536 size=131072 end_off=229444608 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272caf3c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272caf3c00 p_off=246365184 size=131072 end_off=246496256 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c753c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c753c00 p_off=242564096 size=131072 end_off=242695168 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272bff0c00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bff0c00 p_off=234818560 size=131072 end_off=234949632 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27204e0000 off=38666240 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27204e0000 p_off=38666240 size=131072 end_off=38797312 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272bad0c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bad0c00 p_off=229444608 size=131072 end_off=229575680 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272cb13c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cb13c00 p_off=246496256 size=131072 end_off=246627328 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272c010c00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c010c00 p_off=234949632 size=131072 end_off=235080704 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014b20 buffer=0x7f27b94d3ab0 data(host)=0xc0009ca000 dst0=0x7f272b350c00 dst1=0x7f272b7b0c00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272b7b0c00 p_off=226167808 size=131072 end_off=226298880 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720500000 off=38797312 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720500000 p_off=38797312 size=131072 end_off=38928384 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272baf0c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272baf0c00 p_off=229575680 size=131072 end_off=229706752 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272cb33c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cb33c00 p_off=246627328 size=131072 end_off=246758400 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272c030c00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c030c00 p_off=235080704 size=131072 end_off=235211776 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720520000 off=38928384 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720520000 p_off=38928384 size=131072 end_off=39059456 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272cb53c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cb53c00 p_off=246758400 size=131072 end_off=246889472 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272bb10c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c773c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c773c00 p_off=242695168 size=131072 end_off=242826240 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bb10c00 p_off=229706752 size=131072 end_off=229837824 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272ce53c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ce53c00 p_off=249904128 size=131072 end_off=250035200 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272c050c00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c050c00 p_off=235211776 size=131072 end_off=235342848 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272cb73c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272bb30c00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bb30c00 p_off=229837824 size=131072 end_off=229968896 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720540000 off=39059456 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720540000 p_off=39059456 size=131072 end_off=39190528 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cb73c00 p_off=246889472 size=131072 end_off=247020544 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c793c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c793c00 p_off=242826240 size=131072 end_off=242957312 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272ce73c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ce73c00 p_off=250035200 size=131072 end_off=250166272 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272c070c00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720560000 off=39190528 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c070c00 p_off=235342848 size=131072 end_off=235473920 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720560000 p_off=39190528 size=131072 end_off=39321600 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272bb50c00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bb50c00 p_off=229968896 size=131072 end_off=230099968 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272cb93c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cb93c00 p_off=247020544 size=131072 end_off=247151616 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c7b3c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c7b3c00 p_off=242957312 size=131072 end_off=243088384 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272c090c00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c090c00 p_off=235473920 size=131072 end_off=235604992 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272bb70c00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bb70c00 p_off=230099968 size=131072 end_off=230231040 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272cbb3c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cbb3c00 p_off=247151616 size=131072 end_off=247282688 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c7d3c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c7d3c00 p_off=243088384 size=131072 end_off=243219456 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272ce93c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ce93c00 p_off=250166272 size=131072 end_off=250297344 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272bb90c00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bb90c00 p_off=230231040 size=131072 end_off=230362112 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272cbd3c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cbd3c00 p_off=247282688 size=131072 end_off=247413760 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272ceb3c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ceb3c00 p_off=250297344 size=131072 end_off=250428416 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272cbf3c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cbf3c00 p_off=247413760 size=131072 end_off=247544832 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272bbb0c00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bbb0c00 p_off=230362112 size=131072 end_off=230493184 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272ced3c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ced3c00 p_off=250428416 size=131072 end_off=250559488 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272cc13c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cc13c00 p_off=247544832 size=131072 end_off=247675904 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720580000 off=39321600 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720580000 p_off=39321600 size=131072 end_off=39452672 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272bbd0c00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bbd0c00 p_off=230493184 size=131072 end_off=230624256 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272cef3c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cef3c00 p_off=250559488 size=131072 end_off=250690560 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272cc33c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cc33c00 p_off=247675904 size=131072 end_off=247806976 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27205a0000 off=39452672 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27205a0000 p_off=39452672 size=131072 end_off=39583744 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c7f3c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c7f3c00 p_off=243219456 size=131072 end_off=243350528 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272cc53c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cc53c00 p_off=247806976 size=131072 end_off=247938048 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27205c0000 off=39583744 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27205c0000 p_off=39583744 size=131072 end_off=39714816 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272bbf0c00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bbf0c00 p_off=230624256 size=131072 end_off=230755328 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c813c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c813c00 p_off=243350528 size=131072 end_off=243481600 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272cc73c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cc73c00 p_off=247938048 size=131072 end_off=248069120 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27205e0000 off=39714816 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27205e0000 p_off=39714816 size=131072 end_off=39845888 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272bc10c00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bc10c00 p_off=230755328 size=131072 end_off=230886400 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c833c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c833c00 p_off=243481600 size=131072 end_off=243612672 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720600000 off=39845888 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720600000 p_off=39845888 size=131072 end_off=39976960 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014c90 buffer=0x7f27b94d3ab0 data(host)=0xc0009ea000 dst0=0x7f272b7d0c00 dst1=0x7f272bc30c00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272bc30c00 p_off=230886400 size=131072 end_off=231017472 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272cc93c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cc93c00 p_off=248069120 size=131072 end_off=248200192 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720620000 off=39976960 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720620000 p_off=39976960 size=131072 end_off=40108032 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8014e00 buffer=0x7f27b94d3ab0 data(host)=0xc000a0a000 dst0=0x7f272bc50c00 dst1=0x7f272c0b0c00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c0b0c00 p_off=235604992 size=131072 end_off=235736064 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272cf13c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cf13c00 p_off=250690560 size=131072 end_off=250821632 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272ccb3c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ccb3c00 p_off=248200192 size=131072 end_off=248331264 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c853c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c853c00 p_off=243612672 size=131072 end_off=243743744 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720640000 off=40108032 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720640000 p_off=40108032 size=131072 end_off=40239104 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015c60 buffer=0x7f27b94d3ab0 data(host)=0xc000610000 dst0=0x7f272d2d3c00 dst1=0x7f272d2d3c00 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d2d3c00 p_off=254622720 size=3072 end_off=254625792 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720660000 off=40239104 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720660000 p_off=40239104 size=131072 end_off=40370176 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015f40 buffer=0x7f27b94d3ab0 data(host)=0xc000700000 dst0=0x7f272d2d5400 dst1=0x7f272d2d5400 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d2d5400 p_off=254628864 size=3072 end_off=254631936 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272cf33c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272ccd3c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c873c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ccd3c00 p_off=248331264 size=131072 end_off=248462336 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015dd0 buffer=0x7f27b94d3ab0 data(host)=0xc000650000 dst0=0x7f272d2d4800 dst1=0x7f272d2d4800 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d2d4800 p_off=254625792 size=3072 end_off=254628864 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cf33c00 p_off=250821632 size=131072 end_off=250952704 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720680000 off=40370176 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720680000 p_off=40370176 size=131072 end_off=40501248 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80160b0 buffer=0x7f27b94d3ab0 data(host)=0xc000720000 dst0=0x7f272d2d6000 dst1=0x7f272d2d6000 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d2d6000 p_off=254631936 size=3072 end_off=254635008 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272ccf3c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ccf3c00 p_off=248462336 size=131072 end_off=248593408 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272cf53c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cf53c00 p_off=250952704 size=131072 end_off=251083776 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27206a0000 off=40501248 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27206a0000 p_off=40501248 size=131072 end_off=40632320 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d2d6c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d2d6c00 p_off=254635008 size=131072 end_off=254766080 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272cd13c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cd13c00 p_off=248593408 size=131072 end_off=248724480 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016390 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f272d636c00 dst1=0x7f272d636c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d636c00 p_off=258173952 size=131072 end_off=258305024 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272cf73c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cf73c00 p_off=251083776 size=131072 end_off=251214848 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c873c00 p_off=243743744 size=131072 end_off=243874816 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27206c0000 off=40632320 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27206c0000 p_off=40632320 size=131072 end_off=40763392 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d2f6c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d2f6c00 p_off=254766080 size=131072 end_off=254897152 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272cd33c00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cd33c00 p_off=248724480 size=131072 end_off=248855552 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016390 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f272d636c00 dst1=0x7f272d656c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d656c00 p_off=258305024 size=131072 end_off=258436096 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c893c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c893c00 p_off=243874816 size=131072 end_off=244005888 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27206e0000 off=40763392 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27206e0000 p_off=40763392 size=131072 end_off=40894464 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016390 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f272d636c00 dst1=0x7f272d676c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d676c00 p_off=258436096 size=131072 end_off=258567168 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c8b3c00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c8b3c00 p_off=244005888 size=131072 end_off=244136960 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720700000 off=40894464 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720700000 p_off=40894464 size=131072 end_off=41025536 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272cd53c00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cd53c00 p_off=248855552 size=131072 end_off=248986624 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016390 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f272d636c00 dst1=0x7f272d696c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d696c00 p_off=258567168 size=131072 end_off=258698240 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c8d3c00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c8d3c00 p_off=244136960 size=131072 end_off=244268032 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720720000 off=41025536 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720720000 p_off=41025536 size=131072 end_off=41156608 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272cd73c00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cd73c00 p_off=248986624 size=131072 end_off=249117696 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272cf93c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016390 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f272d636c00 dst1=0x7f272d6b6c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d6b6c00 p_off=258698240 size=131072 end_off=258829312 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cf93c00 p_off=251214848 size=131072 end_off=251345920 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272cd93c00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cd93c00 p_off=249117696 size=131072 end_off=249248768 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720740000 off=41156608 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720740000 p_off=41156608 size=131072 end_off=41287680 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d316c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d316c00 p_off=254897152 size=131072 end_off=255028224 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c8f3c00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c8f3c00 p_off=244268032 size=131072 end_off=244399104 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016390 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f272d636c00 dst1=0x7f272d6d6c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d6d6c00 p_off=258829312 size=131072 end_off=258960384 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720760000 off=41287680 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720760000 p_off=41287680 size=131072 end_off=41418752 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d336c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d336c00 p_off=255028224 size=131072 end_off=255159296 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272cfb3c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cfb3c00 p_off=251345920 size=131072 end_off=251476992 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272cdb3c00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cdb3c00 p_off=249248768 size=131072 end_off=249379840 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272cfd3c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cfd3c00 p_off=251476992 size=131072 end_off=251608064 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272cdd3c00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cdd3c00 p_off=249379840 size=131072 end_off=249510912 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016390 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f272d636c00 dst1=0x7f272d6f6c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d6f6c00 p_off=258960384 size=131072 end_off=259091456 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272cdf3c00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cdf3c00 p_off=249510912 size=131072 end_off=249641984 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016390 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f272d636c00 dst1=0x7f272d716c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d716c00 p_off=259091456 size=131072 end_off=259222528 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272ce13c00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ce13c00 p_off=249641984 size=131072 end_off=249773056 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c913c00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c913c00 p_off=244399104 size=131072 end_off=244530176 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d356c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d356c00 p_off=255159296 size=131072 end_off=255290368 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720780000 off=41418752 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720780000 p_off=41418752 size=131072 end_off=41549824 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015980 buffer=0x7f27b94d3ab0 data(host)=0xc000b4a000 dst0=0x7f272c9d3c00 dst1=0x7f272ce33c00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ce33c00 p_off=249773056 size=131072 end_off=249904128 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016390 buffer=0x7f27b94d3ab0 data(host)=0xc000760000 dst0=0x7f272d636c00 dst1=0x7f272d736c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d736c00 p_off=259222528 size=131072 end_off=259353600 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c933c00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c933c00 p_off=244530176 size=131072 end_off=244661248 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27207a0000 off=41549824 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27207a0000 p_off=41549824 size=131072 end_off=41680896 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d376c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27207c0000 off=41680896 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272cff3c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016500 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f272d756c00 dst1=0x7f272d756c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27207c0000 p_off=41680896 size=131072 end_off=41811968 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d756c00 p_off=259353600 size=131072 end_off=259484672 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d376c00 p_off=255290368 size=131072 end_off=255421440 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272dbd6c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272dbd6c00 p_off=264072192 size=131072 end_off=264203264 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c953c00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c953c00 p_off=244661248 size=131072 end_off=244792320 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272cff3c00 p_off=251608064 size=131072 end_off=251739136 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27207e0000 off=41811968 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27207e0000 p_off=41811968 size=131072 end_off=41943040 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016500 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f272d756c00 dst1=0x7f272d776c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d776c00 p_off=259484672 size=131072 end_off=259615744 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272dbf6c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272dbf6c00 p_off=264203264 size=131072 end_off=264334336 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d396c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d396c00 p_off=255421440 size=131072 end_off=255552512 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272d013c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d013c00 p_off=251739136 size=131072 end_off=251870208 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720800000 off=41943040 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720800000 p_off=41943040 size=131072 end_off=42074112 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016500 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f272d756c00 dst1=0x7f272d796c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d796c00 p_off=259615744 size=131072 end_off=259746816 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272dc16c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272dc16c00 p_off=264334336 size=131072 end_off=264465408 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272d033c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d033c00 p_off=251870208 size=131072 end_off=252001280 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d3b6c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d3b6c00 p_off=255552512 size=131072 end_off=255683584 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720820000 off=42074112 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720820000 p_off=42074112 size=131072 end_off=42205184 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016500 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f272d756c00 dst1=0x7f272d7b6c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d7b6c00 p_off=259746816 size=131072 end_off=259877888 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c973c00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c973c00 p_off=244792320 size=131072 end_off=244923392 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272dc36c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272dc36c00 p_off=264465408 size=131072 end_off=264596480 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d3d6c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d3d6c00 p_off=255683584 size=131072 end_off=255814656 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720840000 off=42205184 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720840000 p_off=42205184 size=131072 end_off=42336256 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016500 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f272d756c00 dst1=0x7f272d7d6c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d7d6c00 p_off=259877888 size=131072 end_off=260008960 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c993c00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c993c00 p_off=244923392 size=131072 end_off=245054464 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d3f6c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d3f6c00 p_off=255814656 size=131072 end_off=255945728 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016500 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f272d756c00 dst1=0x7f272d7f6c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d7f6c00 p_off=260008960 size=131072 end_off=260140032 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720860000 off=42336256 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720860000 p_off=42336256 size=131072 end_off=42467328 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272dc56c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272dc56c00 p_off=264596480 size=131072 end_off=264727552 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272d053c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d053c00 p_off=252001280 size=131072 end_off=252132352 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d416c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d416c00 p_off=255945728 size=131072 end_off=256076800 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016500 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f272d756c00 dst1=0x7f272d816c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d816c00 p_off=260140032 size=131072 end_off=260271104 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720880000 off=42467328 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720880000 p_off=42467328 size=131072 end_off=42598400 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015810 buffer=0x7f27b94d3ab0 data(host)=0xc000b2a000 dst0=0x7f272c553c00 dst1=0x7f272c9b3c00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272c9b3c00 p_off=245054464 size=131072 end_off=245185536 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272dc76c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272dc76c00 p_off=264727552 size=131072 end_off=264858624 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d436c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d436c00 p_off=256076800 size=131072 end_off=256207872 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016500 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f272d756c00 dst1=0x7f272d836c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d836c00 p_off=260271104 size=131072 end_off=260402176 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27208a0000 off=42598400 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27208a0000 p_off=42598400 size=131072 end_off=42729472 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272d073c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d073c00 p_off=252132352 size=131072 end_off=252263424 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272dc96c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272dc96c00 p_off=264858624 size=131072 end_off=264989696 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d456c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d456c00 p_off=256207872 size=131072 end_off=256338944 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016500 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f272d756c00 dst1=0x7f272d856c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d856c00 p_off=260402176 size=131072 end_off=260533248 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27208c0000 off=42729472 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27208c0000 p_off=42729472 size=131072 end_off=42860544 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272d093c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d093c00 p_off=252263424 size=131072 end_off=252394496 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272dcb6c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272dcb6c00 p_off=264989696 size=131072 end_off=265120768 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d476c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d476c00 p_off=256338944 size=131072 end_off=256470016 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016500 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f272d756c00 dst1=0x7f272d876c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d876c00 p_off=260533248 size=131072 end_off=260664320 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27208e0000 off=42860544 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27208e0000 p_off=42860544 size=131072 end_off=42991616 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272d0b3c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d0b3c00 p_off=252394496 size=131072 end_off=252525568 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272dcd6c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272dcd6c00 p_off=265120768 size=131072 end_off=265251840 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d496c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d496c00 p_off=256470016 size=131072 end_off=256601088 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016500 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f272d756c00 dst1=0x7f272d896c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d896c00 p_off=260664320 size=131072 end_off=260795392 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720900000 off=42991616 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720900000 p_off=42991616 size=131072 end_off=43122688 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272d0d3c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d0d3c00 p_off=252525568 size=131072 end_off=252656640 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272dcf6c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272dcf6c00 p_off=265251840 size=131072 end_off=265382912 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d4b6c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d4b6c00 p_off=256601088 size=131072 end_off=256732160 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016500 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f272d756c00 dst1=0x7f272d8b6c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d8b6c00 p_off=260795392 size=131072 end_off=260926464 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720920000 off=43122688 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720920000 p_off=43122688 size=131072 end_off=43253760 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272d0f3c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d0f3c00 p_off=252656640 size=131072 end_off=252787712 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272dd16c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272dd16c00 p_off=265382912 size=131072 end_off=265513984 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d4d6c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d4d6c00 p_off=256732160 size=131072 end_off=256863232 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016500 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f272d756c00 dst1=0x7f272d8d6c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d8d6c00 p_off=260926464 size=131072 end_off=261057536 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720940000 off=43253760 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720940000 p_off=43253760 size=131072 end_off=43384832 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272d113c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d113c00 p_off=252787712 size=131072 end_off=252918784 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272dd36c00 off=1441792 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272dd36c00 p_off=265513984 size=131072 end_off=265645056 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016500 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f272d756c00 dst1=0x7f272d8f6c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d8f6c00 p_off=261057536 size=131072 end_off=261188608 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720960000 off=43384832 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720960000 p_off=43384832 size=131072 end_off=43515904 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272d133c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d133c00 p_off=252918784 size=131072 end_off=253049856 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272dd56c00 off=1572864 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272dd56c00 p_off=265645056 size=131072 end_off=265776128 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d4f6c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d4f6c00 p_off=256863232 size=131072 end_off=256994304 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016500 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f272d756c00 dst1=0x7f272d916c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d916c00 p_off=261188608 size=131072 end_off=261319680 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272d153c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d153c00 p_off=253049856 size=131072 end_off=253180928 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272dd76c00 off=1703936 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272dd76c00 p_off=265776128 size=131072 end_off=265907200 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d516c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d516c00 p_off=256994304 size=131072 end_off=257125376 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016500 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f272d756c00 dst1=0x7f272d936c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80167e0 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272e056c00 dst1=0x7f272e056c00 off=0 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272e056c00 p_off=268790784 size=131072 end_off=268921856 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720980000 off=43515904 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d936c00 p_off=261319680 size=131072 end_off=261450752 OOB=0
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720980000 p_off=43515904 size=131072 end_off=43646976 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272d173c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d173c00 p_off=253180928 size=131072 end_off=253312000 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272dd96c00 off=1835008 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272dd96c00 p_off=265907200 size=131072 end_off=266038272 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d536c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d536c00 p_off=257125376 size=131072 end_off=257256448 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80167e0 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272e056c00 dst1=0x7f272e076c00 off=131072 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272e076c00 p_off=268921856 size=131072 end_off=269052928 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272d193c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d193c00 p_off=253312000 size=131072 end_off=253443072 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272ddb6c00 off=1966080 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ddb6c00 p_off=266038272 size=131072 end_off=266169344 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d556c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d556c00 p_off=257256448 size=131072 end_off=257387520 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80167e0 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272e056c00 dst1=0x7f272e096c00 off=262144 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272e096c00 p_off=269052928 size=131072 end_off=269184000 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272d1b3c00 off=3538944 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d1b3c00 p_off=253443072 size=131072 end_off=253574144 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27209a0000 off=43646976 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27209a0000 p_off=43646976 size=131072 end_off=43778048 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272ddd6c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ddd6c00 p_off=266169344 size=131072 end_off=266300416 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80167e0 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272e056c00 dst1=0x7f272e0b6c00 off=393216 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272e0b6c00 p_off=269184000 size=131072 end_off=269315072 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d576c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d576c00 p_off=257387520 size=131072 end_off=257518592 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272d1d3c00 off=3670016 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d1d3c00 p_off=253574144 size=131072 end_off=253705216 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272ddf6c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ddf6c00 p_off=266300416 size=131072 end_off=266431488 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27209c0000 off=43778048 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27209c0000 p_off=43778048 size=131072 end_off=43909120 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80167e0 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272e056c00 dst1=0x7f272e0d6c00 off=524288 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272e0d6c00 p_off=269315072 size=131072 end_off=269446144 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d596c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d596c00 p_off=257518592 size=131072 end_off=257649664 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272d1f3c00 off=3801088 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d1f3c00 p_off=253705216 size=131072 end_off=253836288 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272de16c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272de16c00 p_off=266431488 size=131072 end_off=266562560 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f27209e0000 off=43909120 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f27209e0000 p_off=43909120 size=131072 end_off=44040192 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016500 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f272d756c00 dst1=0x7f272d956c00 off=2097152 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d956c00 p_off=261450752 size=131072 end_off=261581824 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d5b6c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d5b6c00 p_off=257649664 size=131072 end_off=257780736 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272d213c00 off=3932160 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d213c00 p_off=253836288 size=131072 end_off=253967360 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272de36c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272de36c00 p_off=266562560 size=131072 end_off=266693632 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720a00000 off=44040192 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720a00000 p_off=44040192 size=131072 end_off=44171264 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016500 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f272d756c00 dst1=0x7f272d976c00 off=2228224 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d976c00 p_off=261581824 size=131072 end_off=261712896 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d5d6c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d5d6c00 p_off=257780736 size=131072 end_off=257911808 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272d233c00 off=4063232 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d233c00 p_off=253967360 size=131072 end_off=254098432 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272de56c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272de56c00 p_off=266693632 size=131072 end_off=266824704 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720a20000 off=44171264 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720a20000 p_off=44171264 size=131072 end_off=44302336 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016500 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f272d756c00 dst1=0x7f272d996c00 off=2359296 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d996c00 p_off=261712896 size=131072 end_off=261843968 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d5f6c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d5f6c00 p_off=257911808 size=131072 end_off=258042880 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272d253c00 off=4194304 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d253c00 p_off=254098432 size=131072 end_off=254229504 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272de76c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272de76c00 p_off=266824704 size=131072 end_off=266955776 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80167e0 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272e056c00 dst1=0x7f272e0f6c00 off=655360 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272e0f6c00 p_off=269446144 size=131072 end_off=269577216 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016500 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f272d756c00 dst1=0x7f272d9b6c00 off=2490368 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d9b6c00 p_off=261843968 size=131072 end_off=261975040 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016220 buffer=0x7f27b94d3ab0 data(host)=0xc000740000 dst0=0x7f272d2d6c00 dst1=0x7f272d616c00 off=3407872 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d616c00 p_off=258042880 size=131072 end_off=258173952 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272d273c00 off=4325376 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d273c00 p_off=254229504 size=131072 end_off=254360576 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720a40000 off=44302336 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720a40000 p_off=44302336 size=131072 end_off=44433408 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80167e0 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272e056c00 dst1=0x7f272e116c00 off=786432 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272e116c00 p_off=269577216 size=131072 end_off=269708288 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272d293c00 off=4456448 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d293c00 p_off=254360576 size=131072 end_off=254491648 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720a60000 off=44433408 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720a60000 p_off=44433408 size=131072 end_off=44564480 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8015af0 buffer=0x7f27b94d3ab0 data(host)=0xc000530000 dst0=0x7f272ce53c00 dst1=0x7f272d2b3c00 off=4587520 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d2b3c00 p_off=254491648 size=131072 end_off=254622720 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272de96c00 off=2883584 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272de96c00 p_off=266955776 size=131072 end_off=267086848 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80167e0 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272e056c00 dst1=0x7f272e136c00 off=917504 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272e136c00 p_off=269708288 size=131072 end_off=269839360 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720a80000 off=44564480 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720a80000 p_off=44564480 size=131072 end_off=44695552 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016950 buffer=0x7f27b94d3ab0 data(host)=0xc00082e000 dst0=0x7f272e4d6c00 dst1=0x7f272e4d6c00 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272e4d6c00 p_off=273509376 size=3072 end_off=273512448 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272deb6c00 off=3014656 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272deb6c00 p_off=267086848 size=131072 end_off=267217920 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016ac0 buffer=0x7f27b94d3ab0 data(host)=0xc00084e000 dst0=0x7f272e4d7800 dst1=0x7f272e4d7800 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272e4d7800 p_off=273512448 size=3072 end_off=273515520 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016c30 buffer=0x7f27b94d3ab0 data(host)=0xc00088a000 dst0=0x7f272e4d8400 dst1=0x7f272e4d8400 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272e4d8400 p_off=273515520 size=3072 end_off=273518592 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720aa0000 off=44695552 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720aa0000 p_off=44695552 size=131072 end_off=44826624 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80167e0 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272e056c00 dst1=0x7f272e156c00 off=1048576 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272e156c00 p_off=269839360 size=131072 end_off=269970432 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016500 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f272d756c00 dst1=0x7f272d9d6c00 off=2621440 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d9d6c00 p_off=261975040 size=131072 end_off=262106112 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016da0 buffer=0x7f27b94d3ab0 data(host)=0xc0008aa000 dst0=0x7f272e4d9000 dst1=0x7f272e4d9000 off=0 size=3072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272e4d9000 p_off=273518592 size=3072 end_off=273521664 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272ded6c00 off=3145728 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272ded6c00 p_off=267217920 size=131072 end_off=267348992 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80167e0 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272e056c00 dst1=0x7f272e176c00 off=1179648 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272e176c00 p_off=269970432 size=131072 end_off=270101504 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720ac0000 off=44826624 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f2720ac0000 p_off=44826624 size=131072 end_off=44957696 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016500 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f272d756c00 dst1=0x7f272d9f6c00 off=2752512 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] alloc base=0x7f271e000000 len=273521664 p=0x7f272d9f6c00 p_off=262106112 size=131072 end_off=262237184 OOB=0
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016670 buffer=0x7f27b94d3ab0 data(host)=0xc0007a8000 dst0=0x7f272dbd6c00 dst1=0x7f272def6c00 off=3276800 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] cuMemGetAddressRange FAILED cr=709 CUDA_ERROR_CONTEXT_IS_DESTROYED context is destroyed p=0x7f272def6c00
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b800d260 buffer=0x7f27b94d3ab0 data(host)=0xc000630000 dst0=0x7f271e000000 dst1=0x7f2720ae0000 off=44957696 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] cuMemGetAddressRange FAILED cr=709 CUDA_ERROR_CONTEXT_IS_DESTROYED context is destroyed p=0x7f2720ae0000
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b80167e0 buffer=0x7f27b94d3ab0 data(host)=0xc0007c8000 dst0=0x7f272e056c00 dst1=0x7f272e196c00 off=1310720 size=131072 attr0=0(no error) type0=2 attr1=0(no error) type1=2
[GGML-CUDA-DIAG] cuMemGetAddressRange FAILED cr=709 CUDA_ERROR_CONTEXT_IS_DESTROYED context is destroyed p=0x7f272e196c00
time=2026-01-04T07:20:39.292-06:00 level=DEBUG source=server.go:1391 msg="model load progress 0.97"
CUDA error: invalid argument
  current device: 0, in function ggml_backend_cuda_buffer_set_tensor at /var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:849
  cudaMemcpyAsyncReserve((char *)tensor->data + offset, data, size, cudaMemcpyHostToDevice, ((cudaStream_t)0x2))
CUDA error: invalid argument
/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:94: CUDA error
CUDA error: invalid argument
  current device: 0, in function ggml_backend_cuda_buffer_set_tensor at /var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:849
  cudaMemcpyAsyncReserve((char *)tensor->data + offset, data, size, cudaMemcpyHostToDevice, ((cudaStream_t)0x2))
/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:94: CUDA error
[GGML-CUDA-DIAG] dev(ctx)=0 dev(cur)=0 tensor=0x7f27b8016500 buffer=0x7f27b94d3ab0 data(host)=0xc000788000 dst0=0x7f272d756c00 dst1=0x7f272da16c00 off=2883584 size=131072 attr0=0(no error) type0=0 attr1=0(no error) type1=0
[GGML-CUDA-DIAG] cuMemGetAddressRange FAILED cr=500 CUDA_ERROR_NOT_FOUND named symbol not found p=0x7f272da16c00
CUDA error: invalid argument
  current device: 0, in function ggml_backend_cuda_buffer_set_tensor at /var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:849
  cudaMemcpyAsyncReserve((char *)tensor->data + offset, data, size, cudaMemcpyHostToDevice, ((cudaStream_t)0x2))
/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:94: CUDA error
  current device: 0, in function ggml_backend_cuda_buffer_set_tensor at /var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:849
  cudaMemcpyAsyncReserve((char *)tensor->data + offset, data, size, cudaMemcpyHostToDevice, ((cudaStream_t)0x2))
/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:94: CUDA error
[New LWP 16534]
[New LWP 16533]
[New LWP 16532]
[New LWP 16531]
[New LWP 16530]
[New LWP 16529]
[New LWP 16528]
[New LWP 16527]
[New LWP 16526]
[New LWP 16519]
[New LWP 16515]
[New LWP 16514]
[New LWP 16513]
[New LWP 16512]
[New LWP 16511]
[New LWP 16510]
[New LWP 16509]
warning: process 16508 is already traced by process 16535
warning: process 16508 is already traced by process 16535
warning: process 16508 is already traced by process 16535
ptrace: Operation not permitted.ptrace: Operation not permitted.ptrace: Operation not permitted.


No stack.
No stack.No stack.

The program is not being run.
The program is not being run.The program is not being run.

[Thread debugging using libthread_db enabled]
Using host libthread_db library "/lib64/libthread_db.so.1".
0x00007f28206ae6a2 in ?? () from /lib64/libc.so.6
#0  0x00007f28206ae6a2 in ?? () from /lib64/libc.so.6
#1  0x00007f28206a315c in ?? () from /lib64/libc.so.6
#2  0x00007f28206a31a1 in ?? () from /lib64/libc.so.6
#3  0x00007f282070f44b in wait4 () from /lib64/libc.so.6
#4  0x00007f27d802c3d3 in ggml_print_backtrace () from /usr/lib64/ollama/libggml-base.so.0
#5  0x00007f27d802c586 in ggml_abort () from /usr/lib64/ollama/libggml-base.so.0
#6  0x00007f27af541d95 in ggml_cuda_error(char const*, char const*, char const*, int, char const*) () from /usr/lib64/ollama/libggml-cuda.so
#7  0x00007f27af542796 in ?? () from /usr/lib64/ollama/libggml-cuda.so
time=2026-01-04T07:20:39.743-06:00 level=INFO source=server.go:1381 msg="waiting for server to become available" status="llm server not responding"
#8  0x00000000004c7544 in ?? ()
#9  0x00000000000004c0 in ?? ()
#10 0x000000c000582e00 in ?? ()
#11 0x00000000004c58ea in ?? ()
#12 0x00000000004ca37f in ?? ()
#13 0x00007fff47f36328 in ?? ()
#14 0x00000000004ca37f in ?? ()
#15 0x000000000230acc0 in ?? ()
#16 0x0000000000000007 in ?? ()
#17 0x00000000004c57e5 in ?? ()
#18 0x00000000004c576f in ?? ()
#19 0x00007f2800000007 in ?? ()
#20 0x00007fff47f36478 in ?? ()
#21 0x000000000000000a in ?? ()
#22 0x0000000000000007 in ?? ()
#23 0x00007fff47f36478 in ?? ()
#24 0x00007f282063c16e in ?? () from /lib64/libc.so.6
#25 0x00007f282063c229 in __libc_start_main () from /lib64/libc.so.6
#26 0x0000000000442775 in ?? ()
SIGABRT: abort
PC=0x7f28206a84cc m=9 sigcode=18446744073709551610
signal arrived during cgo execution

goroutine 22 gp=0xc000582fc0 m=9 mp=0xc000580808 [syscall]:
runtime.cgocall(0x1207370, 0xc0003fbbb0)
	/usr/lib/go/src/runtime/cgocall.go:167 +0x4b fp=0xc0003fbb88 sp=0xc0003fbb50 pc=0x4bc36b
github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_tensor_set(0x7f27b800d260, 0xc000630000, 0x2ae0000, 0x20000)
	_cgo_gotypes.go:1095 +0x3e fp=0xc0003fbbb0 sp=0xc0003fbb88 pc=0x8f881e
github.com/ollama/ollama/ml/backend/ggml.(*Backend).Load.func3.3(...)
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/ml/backend/ggml/ggml.go:613
github.com/ollama/ollama/ml/backend/ggml.(*Backend).Load.func3()
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/ml/backend/ggml/ggml.go:613 +0xb9f fp=0xc0003fbf78 sp=0xc0003fbbb0 pc=0x9039df
golang.org/x/sync/errgroup.(*Group).Go.func1()
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/vendor/golang.org/x/sync/errgroup/errgroup.go:93 +0x50 fp=0xc0003fbfe0 sp=0xc0003fbf78 pc=0x82ded0
runtime.goexit({})
	/usr/lib/go/src/runtime/asm_amd64.s:1693 +0x1 fp=0xc0003fbfe8 sp=0xc0003fbfe0 pc=0x4c78a1
created by golang.org/x/sync/errgroup.(*Group).Go in goroutine 11
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/vendor/golang.org/x/sync/errgroup/errgroup.go:78 +0x95

goroutine 1 gp=0xc000002380 m=nil [IO wait]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	/usr/lib/go/src/runtime/proc.go:460 +0xce fp=0xc000805790 sp=0xc000805770 pc=0x4bf7ee
runtime.netpollblock(0xc00050f7e0?, 0x454a86?, 0x0?)
	/usr/lib/go/src/runtime/netpoll.go:575 +0xf7 fp=0xc0008057c8 sp=0xc000805790 pc=0x483597
internal/poll.runtime_pollWait(0x7f2820abb400, 0x72)
	/usr/lib/go/src/runtime/netpoll.go:351 +0x85 fp=0xc0008057e8 sp=0xc0008057c8 pc=0x4be9c5
internal/poll.(*pollDesc).wait(0xc0004b5300?, 0x900000036?, 0x0)
	/usr/lib/go/src/internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000805810 sp=0xc0008057e8 pc=0x5474c7
internal/poll.(*pollDesc).waitRead(...)
	/usr/lib/go/src/internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Accept(0xc0004b5300)
	/usr/lib/go/src/internal/poll/fd_unix.go:613 +0x28c fp=0xc0008058b8 sp=0xc000805810 pc=0x54c8ec
net.(*netFD).accept(0xc0004b5300)
	/usr/lib/go/src/net/fd_unix.go:161 +0x29 fp=0xc000805970 sp=0xc0008058b8 pc=0x5b6d69
net.(*TCPListener).accept(0xc00041a400)
	/usr/lib/go/src/net/tcpsock_posix.go:159 +0x1b fp=0xc0008059c0 sp=0xc000805970 pc=0x5cc45b
net.(*TCPListener).Accept(0xc00041a400)
	/usr/lib/go/src/net/tcpsock.go:380 +0x30 fp=0xc0008059f0 sp=0xc0008059c0 pc=0x5cb2f0
net/http.(*onceCloseListener).Accept(0xc0004ba3f0?)
	<autogenerated>:1 +0x24 fp=0xc000805a08 sp=0xc0008059f0 pc=0x7ee084
net/http.(*Server).Serve(0xc0001f7700, {0x191e528, 0xc00041a400})
	/usr/lib/go/src/net/http/server.go:3463 +0x30c fp=0xc000805b38 sp=0xc000805a08 pc=0x7c5a6c
github.com/ollama/ollama/runner/ollamarunner.Execute({0xc0000360a0, 0x4, 0x4})
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/runner/ollamarunner/runner.go:1441 +0x954 fp=0xc000805d08 sp=0xc000805b38 pc=0x9e9a34
github.com/ollama/ollama/runner.Execute({0xc000036080?, 0x0?, 0x0?})
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/runner/runner.go:20 +0xc9 fp=0xc000805d30 sp=0xc000805d08 pc=0x9ea329
github.com/ollama/ollama/cmd.NewCLI.func2(0xc0001f7400?, {0x17347fa?, 0x4?, 0x17347fe?})
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/cmd/cmd.go:1844 +0x45 fp=0xc000805d58 sp=0xc000805d30 pc=0x119ef25
github.com/spf13/cobra.(*Command).execute(0xc0004bd508, {0xc0004ad900, 0x5, 0x5})
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/vendor/github.com/spf13/cobra/command.go:940 +0x88a fp=0xc000805e78 sp=0xc000805d58 pc=0x6304ea
github.com/spf13/cobra.(*Command).ExecuteC(0xc000152f08)
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/vendor/github.com/spf13/cobra/command.go:1068 +0x398 fp=0xc000805f30 sp=0xc000805e78 pc=0x630d18
github.com/spf13/cobra.(*Command).Execute(...)
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/vendor/github.com/spf13/cobra/command.go:992
github.com/spf13/cobra.(*Command).ExecuteContext(...)
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/vendor/github.com/spf13/cobra/command.go:985
main.main()
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/main.go:12 +0x4d fp=0xc000805f50 sp=0xc000805f30 pc=0x119fa0d
runtime.main()
	/usr/lib/go/src/runtime/proc.go:285 +0x29d fp=0xc000805fe0 sp=0xc000805f50 pc=0x48addd
runtime.goexit({})
	/usr/lib/go/src/runtime/asm_amd64.s:1693 +0x1 fp=0xc000805fe8 sp=0xc000805fe0 pc=0x4c78a1

goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	/usr/lib/go/src/runtime/proc.go:460 +0xce fp=0xc000084fa8 sp=0xc000084f88 pc=0x4bf7ee
runtime.goparkunlock(...)
	/usr/lib/go/src/runtime/proc.go:466
runtime.forcegchelper()
	/usr/lib/go/src/runtime/proc.go:373 +0xb3 fp=0xc000084fe0 sp=0xc000084fa8 pc=0x48b113
runtime.goexit({})
	/usr/lib/go/src/runtime/asm_amd64.s:1693 +0x1 fp=0xc000084fe8 sp=0xc000084fe0 pc=0x4c78a1
created by runtime.init.7 in goroutine 1
	/usr/lib/go/src/runtime/proc.go:361 +0x1a

goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]:
runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
	/usr/lib/go/src/runtime/proc.go:460 +0xce fp=0xc000085780 sp=0xc000085760 pc=0x4bf7ee
runtime.goparkunlock(...)
	/usr/lib/go/src/runtime/proc.go:466
runtime.bgsweep(0xc000050080)
	/usr/lib/go/src/runtime/mgcsweep.go:323 +0xdf fp=0xc0000857c8 sp=0xc000085780 pc=0x474e9f
runtime.gcenable.gowrap1()
	/usr/lib/go/src/runtime/mgc.go:212 +0x25 fp=0xc0000857e0 sp=0xc0000857c8 pc=0x468e85
runtime.goexit({})
	/usr/lib/go/src/runtime/asm_amd64.s:1693 +0x1 fp=0xc0000857e8 sp=0xc0000857e0 pc=0x4c78a1
created by runtime.gcenable in goroutine 1
	/usr/lib/go/src/runtime/mgc.go:212 +0x66

goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]:
runtime.gopark(0x272378?, 0x223ab764?, 0x0?, 0x0?, 0x0?)
	/usr/lib/go/src/runtime/proc.go:460 +0xce fp=0xc000085f78 sp=0xc000085f58 pc=0x4bf7ee
runtime.goparkunlock(...)
	/usr/lib/go/src/runtime/proc.go:466
runtime.(*scavengerState).park(0x2309b60)
	/usr/lib/go/src/runtime/mgcscavenge.go:425 +0x49 fp=0xc000085fa8 sp=0xc000085f78 pc=0x472909
runtime.bgscavenge(0xc000050080)
	/usr/lib/go/src/runtime/mgcscavenge.go:658 +0x59 fp=0xc000085fc8 sp=0xc000085fa8 pc=0x472eb9
runtime.gcenable.gowrap2()
	/usr/lib/go/src/runtime/mgc.go:213 +0x25 fp=0xc000085fe0 sp=0xc000085fc8 pc=0x468e25
runtime.goexit({})
	/usr/lib/go/src/runtime/asm_amd64.s:1693 +0x1 fp=0xc000085fe8 sp=0xc000085fe0 pc=0x4c78a1
created by runtime.gcenable in goroutine 1
	/usr/lib/go/src/runtime/mgc.go:213 +0xa5

goroutine 5 gp=0xc000003dc0 m=nil [finalizer wait]:
runtime.gopark(0x49a0b5?, 0x4607e5?, 0xb8?, 0x1?, 0xc000002380?)
	/usr/lib/go/src/runtime/proc.go:460 +0xce fp=0xc000084620 sp=0xc000084600 pc=0x4bf7ee
runtime.runFinalizers()
	/usr/lib/go/src/runtime/mfinal.go:210 +0x107 fp=0xc0000847e0 sp=0xc000084620 pc=0x467d87
runtime.goexit({})
	/usr/lib/go/src/runtime/asm_amd64.s:1693 +0x1 fp=0xc0000847e8 sp=0xc0000847e0 pc=0x4c78a1
created by runtime.createfing in goroutine 1
	/usr/lib/go/src/runtime/mfinal.go:172 +0x3d

goroutine 6 gp=0xc0001d68c0 m=nil [cleanup wait]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	/usr/lib/go/src/runtime/proc.go:460 +0xce fp=0xc000086768 sp=0xc000086748 pc=0x4bf7ee
runtime.goparkunlock(...)
	/usr/lib/go/src/runtime/proc.go:466
runtime.(*cleanupQueue).dequeue(0x230a4c0)
	/usr/lib/go/src/runtime/mcleanup.go:439 +0xc5 fp=0xc0000867a0 sp=0xc000086768 pc=0x464fa5
runtime.runCleanups()
	/usr/lib/go/src/runtime/mcleanup.go:635 +0x45 fp=0xc0000867e0 sp=0xc0000867a0 pc=0x465665
runtime.goexit({})
	/usr/lib/go/src/runtime/asm_amd64.s:1693 +0x1 fp=0xc0000867e8 sp=0xc0000867e0 pc=0x4c78a1
created by runtime.(*cleanupQueue).createGs in goroutine 1
	/usr/lib/go/src/runtime/mcleanup.go:589 +0xa5

goroutine 7 gp=0xc0001d7340 m=nil [GC worker (idle)]:
runtime.gopark(0x137545f0a8314?, 0x0?, 0x0?, 0x0?, 0x0?)
	/usr/lib/go/src/runtime/proc.go:460 +0xce fp=0xc000086f38 sp=0xc000086f18 pc=0x4bf7ee
runtime.gcBgMarkWorker(0xc0000b7880)
	/usr/lib/go/src/runtime/mgc.go:1463 +0xeb fp=0xc000086fc8 sp=0xc000086f38 pc=0x46b56b
runtime.gcBgMarkStartWorkers.gowrap1()
	/usr/lib/go/src/runtime/mgc.go:1373 +0x25 fp=0xc000086fe0 sp=0xc000086fc8 pc=0x46b445
runtime.goexit({})
	/usr/lib/go/src/runtime/asm_amd64.s:1693 +0x1 fp=0xc000086fe8 sp=0xc000086fe0 pc=0x4c78a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/usr/lib/go/src/runtime/mgc.go:1373 +0x105

goroutine 18 gp=0xc000504000 m=nil [GC worker (idle)]:
runtime.gopark(0x137545790087d?, 0x0?, 0x0?, 0x0?, 0x0?)
	/usr/lib/go/src/runtime/proc.go:460 +0xce fp=0xc000080738 sp=0xc000080718 pc=0x4bf7ee
runtime.gcBgMarkWorker(0xc0000b7880)
	/usr/lib/go/src/runtime/mgc.go:1463 +0xeb fp=0xc0000807c8 sp=0xc000080738 pc=0x46b56b
runtime.gcBgMarkStartWorkers.gowrap1()
	/usr/lib/go/src/runtime/mgc.go:1373 +0x25 fp=0xc0000807e0 sp=0xc0000807c8 pc=0x46b445
runtime.goexit({})
	/usr/lib/go/src/runtime/asm_amd64.s:1693 +0x1 fp=0xc0000807e8 sp=0xc0000807e0 pc=0x4c78a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/usr/lib/go/src/runtime/mgc.go:1373 +0x105

goroutine 34 gp=0xc000102380 m=nil [GC worker (idle)]:
runtime.gopark(0x137545f0b29ec?, 0x3?, 0xa8?, 0x3a?, 0x0?)
	/usr/lib/go/src/runtime/proc.go:460 +0xce fp=0xc0003f6f38 sp=0xc0003f6f18 pc=0x4bf7ee
runtime.gcBgMarkWorker(0xc0000b7880)
	/usr/lib/go/src/runtime/mgc.go:1463 +0xeb fp=0xc0003f6fc8 sp=0xc0003f6f38 pc=0x46b56b
runtime.gcBgMarkStartWorkers.gowrap1()
	/usr/lib/go/src/runtime/mgc.go:1373 +0x25 fp=0xc0003f6fe0 sp=0xc0003f6fc8 pc=0x46b445
runtime.goexit({})
	/usr/lib/go/src/runtime/asm_amd64.s:1693 +0x1 fp=0xc0003f6fe8 sp=0xc0003f6fe0 pc=0x4c78a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/usr/lib/go/src/runtime/mgc.go:1373 +0x105

goroutine 35 gp=0xc000102540 m=nil [GC worker (idle)]:
runtime.gopark(0x137545f0a9062?, 0x3?, 0xb9?, 0x33?, 0x0?)
	/usr/lib/go/src/runtime/proc.go:460 +0xce fp=0xc000118f38 sp=0xc000118f18 pc=0x4bf7ee
runtime.gcBgMarkWorker(0xc0000b7880)
	/usr/lib/go/src/runtime/mgc.go:1463 +0xeb fp=0xc000118fc8 sp=0xc000118f38 pc=0x46b56b
runtime.gcBgMarkStartWorkers.gowrap1()
	/usr/lib/go/src/runtime/mgc.go:1373 +0x25 fp=0xc000118fe0 sp=0xc000118fc8 pc=0x46b445
runtime.goexit({})
	/usr/lib/go/src/runtime/asm_amd64.s:1693 +0x1 fp=0xc000118fe8 sp=0xc000118fe0 pc=0x4c78a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/usr/lib/go/src/runtime/mgc.go:1373 +0x105

goroutine 36 gp=0xc000102700 m=nil [GC worker (idle)]:
runtime.gopark(0x137545ce3b5c6?, 0x3?, 0x3a?, 0x36?, 0x0?)
	/usr/lib/go/src/runtime/proc.go:460 +0xce fp=0xc000082738 sp=0xc000082718 pc=0x4bf7ee
runtime.gcBgMarkWorker(0xc0000b7880)
	/usr/lib/go/src/runtime/mgc.go:1463 +0xeb fp=0xc0000827c8 sp=0xc000082738 pc=0x46b56b
runtime.gcBgMarkStartWorkers.gowrap1()
	/usr/lib/go/src/runtime/mgc.go:1373 +0x25 fp=0xc0000827e0 sp=0xc0000827c8 pc=0x46b445
runtime.goexit({})
	/usr/lib/go/src/runtime/asm_amd64.s:1693 +0x1 fp=0xc0000827e8 sp=0xc0000827e0 pc=0x4c78a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/usr/lib/go/src/runtime/mgc.go:1373 +0x105

goroutine 37 gp=0xc0001028c0 m=nil [GC worker (idle)]:
runtime.gopark(0x137545f06f348?, 0x2?, 0x74?, 0xf2?, 0x0?)
	/usr/lib/go/src/runtime/proc.go:460 +0xce fp=0xc000117738 sp=0xc000117718 pc=0x4bf7ee
runtime.gcBgMarkWorker(0xc0000b7880)
	/usr/lib/go/src/runtime/mgc.go:1463 +0xeb fp=0xc0001177c8 sp=0xc000117738 pc=0x46b56b
runtime.gcBgMarkStartWorkers.gowrap1()
	/usr/lib/go/src/runtime/mgc.go:1373 +0x25 fp=0xc0001177e0 sp=0xc0001177c8 pc=0x46b445
runtime.goexit({})
	/usr/lib/go/src/runtime/asm_amd64.s:1693 +0x1 fp=0xc0001177e8 sp=0xc0001177e0 pc=0x4c78a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/usr/lib/go/src/runtime/mgc.go:1373 +0x105

goroutine 8 gp=0xc000582540 m=nil [sync.WaitGroup.Wait]:
runtime.gopark(0x0?, 0x0?, 0x60?, 0xe0?, 0x0?)
	/usr/lib/go/src/runtime/proc.go:460 +0xce fp=0xc000092a90 sp=0xc000092a70 pc=0x4bf7ee
runtime.goparkunlock(...)
	/usr/lib/go/src/runtime/proc.go:466
runtime.semacquire1(0xc00022edd8, 0x0, 0x1, 0x0, 0x19)
	/usr/lib/go/src/runtime/sema.go:192 +0x21d fp=0xc000092af8 sp=0xc000092a90 pc=0x49eb1d
sync.runtime_SemacquireWaitGroup(0x0?, 0x0?)
	/usr/lib/go/src/runtime/sema.go:114 +0x2e fp=0xc000092b30 sp=0xc000092af8 pc=0x4c120e
sync.(*WaitGroup).Wait(0xc00022edd0)
	/usr/lib/go/src/sync/waitgroup.go:206 +0x85 fp=0xc000092b58 sp=0xc000092b30 pc=0x4d3505
github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc00022ed20, {0x1920bc0, 0xc0004ad9a0})
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/runner/ollamarunner/runner.go:441 +0x45 fp=0xc000092fb8 sp=0xc000092b58 pc=0x9e04a5
github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap1()
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/runner/ollamarunner/runner.go:1418 +0x28 fp=0xc000092fe0 sp=0xc000092fb8 pc=0x9e9ca8
runtime.goexit({})
	/usr/lib/go/src/runtime/asm_amd64.s:1693 +0x1 fp=0xc000092fe8 sp=0xc000092fe0 pc=0x4c78a1
created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/runner/ollamarunner/runner.go:1418 +0x4c9

goroutine 9 gp=0xc000582700 m=nil [sync.Cond.Wait]:
runtime.gopark(0x0?, 0xe7791f701?, 0x40?, 0x99?, 0x547960?)
	/usr/lib/go/src/runtime/proc.go:460 +0xce fp=0xc00055fa98 sp=0xc00055fa78 pc=0x4bf7ee
runtime.goparkunlock(...)
	/usr/lib/go/src/runtime/proc.go:466
sync.runtime_notifyListWait(0xc00052c150, 0x6)
	/usr/lib/go/src/runtime/sema.go:606 +0x159 fp=0xc00055fae8 sp=0xc00055fa98 pc=0x4c1439
sync.(*Cond).Wait(0xc000138400?)
	/usr/lib/go/src/sync/cond.go:71 +0x73 fp=0xc00055fb20 sp=0xc00055fae8 pc=0x4d1733
net/http.(*connReader).abortPendingRead(0xc00052c080)
	/usr/lib/go/src/net/http/server.go:750 +0x96 fp=0xc00055fb70 sp=0xc00055fb20 pc=0x7ba836
net/http.(*response).finishRequest(0xc00011c000)
	/usr/lib/go/src/net/http/server.go:1712 +0x87 fp=0xc00055fb90 sp=0xc00055fb70 pc=0x7bf407
net/http.(*conn).serve(0xc0004ba3f0, {0x1920b88, 0xc0005193b0})
	/usr/lib/go/src/net/http/server.go:2116 +0x6a5 fp=0xc00055ffb8 sp=0xc00055fb90 pc=0x7c01e5
net/http.(*Server).Serve.gowrap3()
	/usr/lib/go/src/net/http/server.go:3493 +0x28 fp=0xc00055ffe0 sp=0xc00055ffb8 pc=0x7c5e68
runtime.goexit({})
	/usr/lib/go/src/runtime/asm_amd64.s:1693 +0x1 fp=0xc00055ffe8 sp=0xc00055ffe0 pc=0x4c78a1
created by net/http.(*Server).Serve in goroutine 1
	/usr/lib/go/src/net/http/server.go:3493 +0x485

goroutine 11 gp=0xc000103180 m=nil [sync.WaitGroup.Wait]:
runtime.gopark(0x300000002?, 0xc0003ced50?, 0x80?, 0xe1?, 0xc000103180?)
	/usr/lib/go/src/runtime/proc.go:460 +0xce fp=0xc0003cecd8 sp=0xc0003cecb8 pc=0x4bf7ee
runtime.goparkunlock(...)
	/usr/lib/go/src/runtime/proc.go:466
runtime.semacquire1(0xc00023a010, 0x0, 0x1, 0x0, 0x19)
	/usr/lib/go/src/runtime/sema.go:192 +0x21d fp=0xc0003ced40 sp=0xc0003cecd8 pc=0x49eb1d
sync.runtime_SemacquireWaitGroup(0x18?, 0x8?)
	/usr/lib/go/src/runtime/sema.go:114 +0x2e fp=0xc0003ced78 sp=0xc0003ced40 pc=0x4c120e
sync.(*WaitGroup).Wait(0xc00023a008)
	/usr/lib/go/src/sync/waitgroup.go:206 +0x85 fp=0xc0003ceda0 sp=0xc0003ced78 pc=0x4d3505
golang.org/x/sync/errgroup.(*Group).Wait(0xc00023a000)
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/vendor/golang.org/x/sync/errgroup/errgroup.go:56 +0x1e fp=0xc0003cedc0 sp=0xc0003ceda0 pc=0x82dd7e
github.com/ollama/ollama/ml/backend/ggml.(*Backend).Load(0xc0000e36b0, {0x1920c68, 0x23d5ee0}, 0xc000056010)
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/ml/backend/ggml/ggml.go:640 +0x7e7 fp=0xc0003cef70 sp=0xc0003cedc0 pc=0x902d27
github.com/ollama/ollama/runner/ollamarunner.(*Server).loadModel(0xc00022ed20)
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/runner/ollamarunner/runner.go:1247 +0x92 fp=0xc0003cefc8 sp=0xc0003cef70 pc=0x9e7732
github.com/ollama/ollama/runner/ollamarunner.(*Server).load.gowrap2()
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/runner/ollamarunner/runner.go:1335 +0x25 fp=0xc0003cefe0 sp=0xc0003cefc8 pc=0x9e8585
runtime.goexit({})
	/usr/lib/go/src/runtime/asm_amd64.s:1693 +0x1 fp=0xc0003cefe8 sp=0xc0003cefe0 pc=0x4c78a1
created by github.com/ollama/ollama/runner/ollamarunner.(*Server).load in goroutine 9
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/runner/ollamarunner/runner.go:1335 +0x60a

goroutine 138 gp=0xc000582e00 m=0 mp=0x230cae0 [syscall]:
runtime.cgocall(0x1207370, 0xc0003d1bb0)
	/usr/lib/go/src/runtime/cgocall.go:167 +0x4b fp=0xc0003d1b88 sp=0xc0003d1b50 pc=0x4bc36b
github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_tensor_set(0x7f27b8016670, 0xc0007a8000, 0x320000, 0x20000)
	_cgo_gotypes.go:1095 +0x3e fp=0xc0003d1bb0 sp=0xc0003d1b88 pc=0x8f881e
github.com/ollama/ollama/ml/backend/ggml.(*Backend).Load.func3.3(...)
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/ml/backend/ggml/ggml.go:613
github.com/ollama/ollama/ml/backend/ggml.(*Backend).Load.func3()
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/ml/backend/ggml/ggml.go:613 +0xb9f fp=0xc0003d1f78 sp=0xc0003d1bb0 pc=0x9039df
golang.org/x/sync/errgroup.(*Group).Go.func1()
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/vendor/golang.org/x/sync/errgroup/errgroup.go:93 +0x50 fp=0xc0003d1fe0 sp=0xc0003d1f78 pc=0x82ded0
runtime.goexit({})
	/usr/lib/go/src/runtime/asm_amd64.s:1693 +0x1 fp=0xc0003d1fe8 sp=0xc0003d1fe0 pc=0x4c78a1
created by golang.org/x/sync/errgroup.(*Group).Go in goroutine 11
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/vendor/golang.org/x/sync/errgroup/errgroup.go:78 +0x95

goroutine 149 gp=0xc000583180 m=12 mp=0xc000101808 [syscall]:
runtime.cgocall(0x1207370, 0xc000095bb0)
	/usr/lib/go/src/runtime/cgocall.go:167 +0x4b fp=0xc000095b88 sp=0xc000095b50 pc=0x4bc36b
github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_tensor_set(0x7f27b8016500, 0xc000788000, 0x2c0000, 0x20000)
	_cgo_gotypes.go:1095 +0x3e fp=0xc000095bb0 sp=0xc000095b88 pc=0x8f881e
github.com/ollama/ollama/ml/backend/ggml.(*Backend).Load.func3.3(...)
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/ml/backend/ggml/ggml.go:613
github.com/ollama/ollama/ml/backend/ggml.(*Backend).Load.func3()
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/ml/backend/ggml/ggml.go:613 +0xb9f fp=0xc000095f78 sp=0xc000095bb0 pc=0x9039df
golang.org/x/sync/errgroup.(*Group).Go.func1()
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/vendor/golang.org/x/sync/errgroup/errgroup.go:93 +0x50 fp=0xc000095fe0 sp=0xc000095f78 pc=0x82ded0
runtime.goexit({})
	/usr/lib/go/src/runtime/asm_amd64.s:1693 +0x1 fp=0xc000095fe8 sp=0xc000095fe0 pc=0x4c78a1
created by golang.org/x/sync/errgroup.(*Group).Go in goroutine 11
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/vendor/golang.org/x/sync/errgroup/errgroup.go:78 +0x95

goroutine 119 gp=0xc000583340 m=7 mp=0xc000580008 [syscall]:
runtime.cgocall(0x1207370, 0xc000093bb0)
	/usr/lib/go/src/runtime/cgocall.go:167 +0x4b fp=0xc000093b88 sp=0xc000093b50 pc=0x4bc36b
github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_tensor_set(0x7f27b80167e0, 0xc0007c8000, 0x140000, 0x20000)
	_cgo_gotypes.go:1095 +0x3e fp=0xc000093bb0 sp=0xc000093b88 pc=0x8f881e
github.com/ollama/ollama/ml/backend/ggml.(*Backend).Load.func3.3(...)
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/ml/backend/ggml/ggml.go:613
github.com/ollama/ollama/ml/backend/ggml.(*Backend).Load.func3()
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/ml/backend/ggml/ggml.go:613 +0xb9f fp=0xc000093f78 sp=0xc000093bb0 pc=0x9039df
golang.org/x/sync/errgroup.(*Group).Go.func1()
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/vendor/golang.org/x/sync/errgroup/errgroup.go:93 +0x50 fp=0xc000093fe0 sp=0xc000093f78 pc=0x82ded0
runtime.goexit({})
	/usr/lib/go/src/runtime/asm_amd64.s:1693 +0x1 fp=0xc000093fe8 sp=0xc000093fe0 pc=0x4c78a1
created by golang.org/x/sync/errgroup.(*Group).Go in goroutine 11
	/var/tmp/portage/sci-ml/ollama-9999/work/ollama-9999/vendor/golang.org/x/sync/errgroup/errgroup.go:78 +0x95

goroutine 110 gp=0xc0001d7880 m=nil [runnable]:
net/http.(*connReader).startBackgroundRead.gowrap2()
	/usr/lib/go/src/net/http/server.go:698 fp=0xc00024ffe0 sp=0xc00024ffd8 pc=0x7ba560
runtime.goexit({})
	/usr/lib/go/src/runtime/asm_amd64.s:1693 +0x1 fp=0xc00024ffe8 sp=0xc00024ffe0 pc=0x4c78a1
created by net/http.(*connReader).startBackgroundRead in goroutine 9
	/usr/lib/go/src/net/http/server.go:698 +0xb6

rax    0x0
rbx    0x408e
rcx    0x7f28206a84cc
rdx    0x6
rdi    0x407c
rsi    0x408e
rbp    0x7f27afb38575
rsp    0x7f27621fe240
r8     0x0
r9     0x0
r10    0x0
r11    0x246
r12    0x5e
r13    0x6
r14    0x7f27d24983a7
r15    0x2c5
rip    0x7f28206a84cc
rflags 0x246
cs     0x33
fs     0x0
gs     0x0
[Inferior 1 (process 16508) detached]
time=2026-01-04T07:20:39.918-06:00 level=ERROR source=server.go:302 msg="llama runner terminated" error="exit status 2"
time=2026-01-04T07:20:39.994-06:00 level=ERROR source=sched.go:523 msg="error loading llama server" error="llama runner process has terminated: CUDA error"
time=2026-01-04T07:20:39.994-06:00 level=DEBUG source=sched.go:525 msg="triggering expiration for failed load" runner.name=registry.ollama.ai/library/nomic-embed-text:latest runner.inference="[{ID:GPU-81cc0f98-96b6-0d33-bfa1-5989f1d84393 Library:CUDA}]" runner.size="567.6 MiB" runner.vram="567.6 MiB" runner.parallel=1 runner.pid=16508 runner.model=/home/nic/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6 runner.num_ctx=8192
time=2026-01-04T07:20:39.994-06:00 level=DEBUG source=sched.go:311 msg="runner expired event received" runner.name=registry.ollama.ai/library/nomic-embed-text:latest runner.inference="[{ID:GPU-81cc0f98-96b6-0d33-bfa1-5989f1d84393 Library:CUDA}]" runner.size="567.6 MiB" runner.vram="567.6 MiB" runner.parallel=1 runner.pid=16508 runner.model=/home/nic/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6 runner.num_ctx=8192
time=2026-01-04T07:20:39.994-06:00 level=DEBUG source=sched.go:326 msg="got lock to unload expired event" runner.name=registry.ollama.ai/library/nomic-embed-text:latest runner.inference="[{ID:GPU-81cc0f98-96b6-0d33-bfa1-5989f1d84393 Library:CUDA}]" runner.size="567.6 MiB" runner.vram="567.6 MiB" runner.parallel=1 runner.pid=16508 runner.model=/home/nic/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6 runner.num_ctx=8192
time=2026-01-04T07:20:39.994-06:00 level=DEBUG source=sched.go:349 msg="starting background wait for VRAM recovery" runner.name=registry.ollama.ai/library/nomic-embed-text:latest runner.inference="[{ID:GPU-81cc0f98-96b6-0d33-bfa1-5989f1d84393 Library:CUDA}]" runner.size="567.6 MiB" runner.vram="567.6 MiB" runner.parallel=1 runner.pid=16508 runner.model=/home/nic/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6 runner.num_ctx=8192
time=2026-01-04T07:20:39.994-06:00 level=DEBUG source=runner.go:264 msg="refreshing free memory"
[GIN] 2026/01/04 - 07:20:39 | 500 |  1.910969351s |       127.0.0.1 | POST     "/api/embed"
time=2026-01-04T07:20:40.004-06:00 level=DEBUG source=runner.go:312 msg="existing runner discovery took" duration=10.246006ms
time=2026-01-04T07:20:40.004-06:00 level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
time=2026-01-04T07:20:40.005-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 34937"
time=2026-01-04T07:20:40.005-06:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_DEBUG=1 PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/bin:/usr/lib/llvm/21/bin:/usr/lib/llvm/20/bin:/opt/cuda/bin:/home/nic/.local/bin:/home/nic/bin LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends OLLAMA_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends
time=2026-01-04T07:20:40.197-06:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=192.65477ms OLLAMA_LIBRARY_PATH="[/usr/lib64/ollama /usr/lib64/ollama/backends]" extra_envs=map[]
time=2026-01-04T07:20:40.197-06:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=203.090199ms
time=2026-01-04T07:20:40.197-06:00 level=DEBUG source=server.go:1812 msg="stopping llama server" pid=16508
time=2026-01-04T07:20:40.197-06:00 level=DEBUG source=sched.go:358 msg="runner terminated and removed from list, blocking for VRAM recovery" runner.size="567.6 MiB" runner.vram="567.6 MiB" runner.parallel=1 runner.pid=16508 runner.model=/home/nic/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6
time=2026-01-04T07:20:40.448-06:00 level=DEBUG source=runner.go:264 msg="refreshing free memory"
time=2026-01-04T07:20:40.449-06:00 level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
time=2026-01-04T07:20:40.449-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 33909"
time=2026-01-04T07:20:40.449-06:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_DEBUG=1 PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/bin:/usr/lib/llvm/21/bin:/usr/lib/llvm/20/bin:/opt/cuda/bin:/home/nic/.local/bin:/home/nic/bin LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends OLLAMA_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends
time=2026-01-04T07:20:40.644-06:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=195.286631ms OLLAMA_LIBRARY_PATH="[/usr/lib64/ollama /usr/lib64/ollama/backends]" extra_envs=map[]
time=2026-01-04T07:20:40.644-06:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=195.565311ms
time=2026-01-04T07:20:40.698-06:00 level=DEBUG source=runner.go:264 msg="refreshing free memory"
time=2026-01-04T07:20:40.698-06:00 level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
time=2026-01-04T07:20:40.698-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 42147"
time=2026-01-04T07:20:40.698-06:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_DEBUG=1 PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/bin:/usr/lib/llvm/21/bin:/usr/lib/llvm/20/bin:/opt/cuda/bin:/home/nic/.local/bin:/home/nic/bin LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends OLLAMA_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends
time=2026-01-04T07:20:40.894-06:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=195.269664ms OLLAMA_LIBRARY_PATH="[/usr/lib64/ollama /usr/lib64/ollama/backends]" extra_envs=map[]
time=2026-01-04T07:20:40.894-06:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=195.496645ms
time=2026-01-04T07:20:40.948-06:00 level=DEBUG source=runner.go:264 msg="refreshing free memory"
time=2026-01-04T07:20:40.948-06:00 level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
time=2026-01-04T07:20:40.948-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 37789"
time=2026-01-04T07:20:40.948-06:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_DEBUG=1 PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/bin:/usr/lib/llvm/21/bin:/usr/lib/llvm/20/bin:/opt/cuda/bin:/home/nic/.local/bin:/home/nic/bin LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends OLLAMA_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends
time=2026-01-04T07:20:41.168-06:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=220.008986ms OLLAMA_LIBRARY_PATH="[/usr/lib64/ollama /usr/lib64/ollama/backends]" extra_envs=map[]
time=2026-01-04T07:20:41.168-06:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=220.197365ms
time=2026-01-04T07:20:41.198-06:00 level=DEBUG source=runner.go:264 msg="refreshing free memory"
time=2026-01-04T07:20:41.198-06:00 level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
time=2026-01-04T07:20:41.198-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 42427"
time=2026-01-04T07:20:41.198-06:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_DEBUG=1 PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/bin:/usr/lib/llvm/21/bin:/usr/lib/llvm/20/bin:/opt/cuda/bin:/home/nic/.local/bin:/home/nic/bin LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends OLLAMA_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends
time=2026-01-04T07:20:41.439-06:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=240.713561ms OLLAMA_LIBRARY_PATH="[/usr/lib64/ollama /usr/lib64/ollama/backends]" extra_envs=map[]
time=2026-01-04T07:20:41.439-06:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=240.949478ms
time=2026-01-04T07:20:41.448-06:00 level=DEBUG source=runner.go:264 msg="refreshing free memory"
time=2026-01-04T07:20:41.448-06:00 level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
time=2026-01-04T07:20:41.448-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 40795"
time=2026-01-04T07:20:41.448-06:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_DEBUG=1 PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/bin:/usr/lib/llvm/21/bin:/usr/lib/llvm/20/bin:/opt/cuda/bin:/home/nic/.local/bin:/home/nic/bin LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends OLLAMA_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends
time=2026-01-04T07:20:41.701-06:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=253.198487ms OLLAMA_LIBRARY_PATH="[/usr/lib64/ollama /usr/lib64/ollama/backends]" extra_envs=map[]
time=2026-01-04T07:20:41.701-06:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=253.400769ms
time=2026-01-04T07:20:41.701-06:00 level=DEBUG source=runner.go:264 msg="refreshing free memory"
time=2026-01-04T07:20:41.701-06:00 level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
time=2026-01-04T07:20:41.702-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 37059"
time=2026-01-04T07:20:41.702-06:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_DEBUG=1 PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/bin:/usr/lib/llvm/21/bin:/usr/lib/llvm/20/bin:/opt/cuda/bin:/home/nic/.local/bin:/home/nic/bin LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends OLLAMA_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends
time=2026-01-04T07:20:41.942-06:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=240.241435ms OLLAMA_LIBRARY_PATH="[/usr/lib64/ollama /usr/lib64/ollama/backends]" extra_envs=map[]
time=2026-01-04T07:20:41.942-06:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=240.388918ms
time=2026-01-04T07:20:41.948-06:00 level=DEBUG source=runner.go:264 msg="refreshing free memory"
time=2026-01-04T07:20:41.948-06:00 level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
time=2026-01-04T07:20:41.948-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 42207"
time=2026-01-04T07:20:41.948-06:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_DEBUG=1 PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/bin:/usr/lib/llvm/21/bin:/usr/lib/llvm/20/bin:/opt/cuda/bin:/home/nic/.local/bin:/home/nic/bin LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends OLLAMA_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends
time=2026-01-04T07:20:42.192-06:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=243.929993ms OLLAMA_LIBRARY_PATH="[/usr/lib64/ollama /usr/lib64/ollama/backends]" extra_envs=map[]
time=2026-01-04T07:20:42.192-06:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=244.11537ms
time=2026-01-04T07:20:42.198-06:00 level=DEBUG source=runner.go:264 msg="refreshing free memory"
time=2026-01-04T07:20:42.198-06:00 level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
time=2026-01-04T07:20:42.199-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 42365"
time=2026-01-04T07:20:42.199-06:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_DEBUG=1 PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/bin:/usr/lib/llvm/21/bin:/usr/lib/llvm/20/bin:/opt/cuda/bin:/home/nic/.local/bin:/home/nic/bin LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends OLLAMA_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends
time=2026-01-04T07:20:42.438-06:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=239.245878ms OLLAMA_LIBRARY_PATH="[/usr/lib64/ollama /usr/lib64/ollama/backends]" extra_envs=map[]
time=2026-01-04T07:20:42.438-06:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=239.478769ms
time=2026-01-04T07:20:42.449-06:00 level=DEBUG source=runner.go:264 msg="refreshing free memory"
time=2026-01-04T07:20:42.449-06:00 level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
time=2026-01-04T07:20:42.449-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 36029"
time=2026-01-04T07:20:42.449-06:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_DEBUG=1 PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/bin:/usr/lib/llvm/21/bin:/usr/lib/llvm/20/bin:/opt/cuda/bin:/home/nic/.local/bin:/home/nic/bin LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends OLLAMA_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends
time=2026-01-04T07:20:42.705-06:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=255.565265ms OLLAMA_LIBRARY_PATH="[/usr/lib64/ollama /usr/lib64/ollama/backends]" extra_envs=map[]
time=2026-01-04T07:20:42.705-06:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=255.769096ms
time=2026-01-04T07:20:42.705-06:00 level=DEBUG source=runner.go:264 msg="refreshing free memory"
time=2026-01-04T07:20:42.705-06:00 level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
time=2026-01-04T07:20:42.705-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 34891"
time=2026-01-04T07:20:42.705-06:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_DEBUG=1 PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/bin:/usr/lib/llvm/21/bin:/usr/lib/llvm/20/bin:/opt/cuda/bin:/home/nic/.local/bin:/home/nic/bin LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends OLLAMA_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends
time=2026-01-04T07:20:42.951-06:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=246.070112ms OLLAMA_LIBRARY_PATH="[/usr/lib64/ollama /usr/lib64/ollama/backends]" extra_envs=map[]
time=2026-01-04T07:20:42.951-06:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=246.208026ms
time=2026-01-04T07:20:42.951-06:00 level=DEBUG source=runner.go:264 msg="refreshing free memory"
time=2026-01-04T07:20:42.951-06:00 level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
time=2026-01-04T07:20:42.951-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 38833"
time=2026-01-04T07:20:42.951-06:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_DEBUG=1 PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/bin:/usr/lib/llvm/21/bin:/usr/lib/llvm/20/bin:/opt/cuda/bin:/home/nic/.local/bin:/home/nic/bin LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends OLLAMA_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends
time=2026-01-04T07:20:43.195-06:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=243.610393ms OLLAMA_LIBRARY_PATH="[/usr/lib64/ollama /usr/lib64/ollama/backends]" extra_envs=map[]
time=2026-01-04T07:20:43.195-06:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=243.746881ms
time=2026-01-04T07:20:43.198-06:00 level=DEBUG source=runner.go:264 msg="refreshing free memory"
time=2026-01-04T07:20:43.198-06:00 level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
time=2026-01-04T07:20:43.198-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 39173"
time=2026-01-04T07:20:43.198-06:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_DEBUG=1 PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/bin:/usr/lib/llvm/21/bin:/usr/lib/llvm/20/bin:/opt/cuda/bin:/home/nic/.local/bin:/home/nic/bin LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends OLLAMA_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends
time=2026-01-04T07:20:43.442-06:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=244.250204ms OLLAMA_LIBRARY_PATH="[/usr/lib64/ollama /usr/lib64/ollama/backends]" extra_envs=map[]
time=2026-01-04T07:20:43.442-06:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=244.425288ms
time=2026-01-04T07:20:43.448-06:00 level=DEBUG source=runner.go:264 msg="refreshing free memory"
time=2026-01-04T07:20:43.448-06:00 level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
time=2026-01-04T07:20:43.449-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 34959"
time=2026-01-04T07:20:43.449-06:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_DEBUG=1 PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/bin:/usr/lib/llvm/21/bin:/usr/lib/llvm/20/bin:/opt/cuda/bin:/home/nic/.local/bin:/home/nic/bin LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends OLLAMA_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends
time=2026-01-04T07:20:43.709-06:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=260.375882ms OLLAMA_LIBRARY_PATH="[/usr/lib64/ollama /usr/lib64/ollama/backends]" extra_envs=map[]
time=2026-01-04T07:20:43.709-06:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=260.577492ms
time=2026-01-04T07:20:43.709-06:00 level=DEBUG source=runner.go:264 msg="refreshing free memory"
time=2026-01-04T07:20:43.709-06:00 level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
time=2026-01-04T07:20:43.709-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 35413"
time=2026-01-04T07:20:43.709-06:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_DEBUG=1 PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/bin:/usr/lib/llvm/21/bin:/usr/lib/llvm/20/bin:/opt/cuda/bin:/home/nic/.local/bin:/home/nic/bin LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends OLLAMA_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends
time=2026-01-04T07:20:43.962-06:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=253.078568ms OLLAMA_LIBRARY_PATH="[/usr/lib64/ollama /usr/lib64/ollama/backends]" extra_envs=map[]
time=2026-01-04T07:20:43.962-06:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=253.205184ms
time=2026-01-04T07:20:43.962-06:00 level=DEBUG source=runner.go:264 msg="refreshing free memory"
time=2026-01-04T07:20:43.962-06:00 level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
time=2026-01-04T07:20:43.962-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 37987"
time=2026-01-04T07:20:43.962-06:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_DEBUG=1 PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/bin:/usr/lib/llvm/21/bin:/usr/lib/llvm/20/bin:/opt/cuda/bin:/home/nic/.local/bin:/home/nic/bin LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends OLLAMA_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends
time=2026-01-04T07:20:44.218-06:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=255.416466ms OLLAMA_LIBRARY_PATH="[/usr/lib64/ollama /usr/lib64/ollama/backends]" extra_envs=map[]
time=2026-01-04T07:20:44.218-06:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=255.540978ms
time=2026-01-04T07:20:44.218-06:00 level=DEBUG source=runner.go:264 msg="refreshing free memory"
time=2026-01-04T07:20:44.218-06:00 level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
time=2026-01-04T07:20:44.218-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 35805"
time=2026-01-04T07:20:44.218-06:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_DEBUG=1 PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/bin:/usr/lib/llvm/21/bin:/usr/lib/llvm/20/bin:/opt/cuda/bin:/home/nic/.local/bin:/home/nic/bin LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends OLLAMA_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends
time=2026-01-04T07:20:44.475-06:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=256.958457ms OLLAMA_LIBRARY_PATH="[/usr/lib64/ollama /usr/lib64/ollama/backends]" extra_envs=map[]
time=2026-01-04T07:20:44.475-06:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=257.135462ms
time=2026-01-04T07:20:44.475-06:00 level=DEBUG source=runner.go:264 msg="refreshing free memory"
time=2026-01-04T07:20:44.475-06:00 level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
time=2026-01-04T07:20:44.475-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 43005"
time=2026-01-04T07:20:44.475-06:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_DEBUG=1 PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/bin:/usr/lib/llvm/21/bin:/usr/lib/llvm/20/bin:/opt/cuda/bin:/home/nic/.local/bin:/home/nic/bin LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends OLLAMA_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends
time=2026-01-04T07:20:44.735-06:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=260.2816ms OLLAMA_LIBRARY_PATH="[/usr/lib64/ollama /usr/lib64/ollama/backends]" extra_envs=map[]
time=2026-01-04T07:20:44.735-06:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=260.412461ms
time=2026-01-04T07:20:44.735-06:00 level=DEBUG source=runner.go:264 msg="refreshing free memory"
time=2026-01-04T07:20:44.735-06:00 level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
time=2026-01-04T07:20:44.736-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 44317"
time=2026-01-04T07:20:44.736-06:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_DEBUG=1 PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/bin:/usr/lib/llvm/21/bin:/usr/lib/llvm/20/bin:/opt/cuda/bin:/home/nic/.local/bin:/home/nic/bin LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends OLLAMA_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends
time=2026-01-04T07:20:44.996-06:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=260.757095ms OLLAMA_LIBRARY_PATH="[/usr/lib64/ollama /usr/lib64/ollama/backends]" extra_envs=map[]
time=2026-01-04T07:20:44.996-06:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=260.891103ms
time=2026-01-04T07:20:44.996-06:00 level=DEBUG source=runner.go:264 msg="refreshing free memory"
time=2026-01-04T07:20:44.996-06:00 level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
time=2026-01-04T07:20:44.997-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 37217"
time=2026-01-04T07:20:44.997-06:00 level=DEBUG source=server.go:430 msg=subprocess OLLAMA_DEBUG=1 PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/bin:/usr/lib/llvm/21/bin:/usr/lib/llvm/20/bin:/opt/cuda/bin:/home/nic/.local/bin:/home/nic/bin LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends OLLAMA_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64/ollama/backends
time=2026-01-04T07:20:45.198-06:00 level=INFO source=runner.go:464 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[/usr/lib64/ollama /usr/lib64/ollama/backends]" extra_envs=map[] error="failed to finish discovery before timeout"
time=2026-01-04T07:20:45.198-06:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=202.090297ms OLLAMA_LIBRARY_PATH="[/usr/lib64/ollama /usr/lib64/ollama/backends]" extra_envs=map[]
time=2026-01-04T07:20:45.198-06:00 level=WARN source=runner.go:356 msg="unable to refresh free memory, using old values"
time=2026-01-04T07:20:45.198-06:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=202.196458ms
time=2026-01-04T07:20:45.198-06:00 level=DEBUG source=sched.go:718 msg="gpu VRAM usage didn't recover within timeout" seconds=5.204384955 free_before="8.7 GiB" free_now="8.7 GiB" runner.size="567.6 MiB" runner.vram="567.6 MiB" runner.parallel=1 runner.pid=16508 runner.model=/home/nic/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6
time=2026-01-04T07:20:45.199-06:00 level=DEBUG source=sched.go:361 msg="sending an unloaded event" runner.size="567.6 MiB" runner.vram="567.6 MiB" runner.parallel=1 runner.pid=16508 runner.model=/home/nic/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6
time=2026-01-04T07:20:45.199-06:00 level=DEBUG source=sched.go:259 msg="ignoring unload event with no pending requests"