{"build_commit": "1c1409e1", "build_number": 6865, "cpu_info": "AMD Eng Sample: 100-000001243-50_Y", "gpu_info": "Radeon 8060S Graphics", "backends": "ROCm", "model_filename": "/models/gguf/gpt-oss-20b-F16.gguf", "model_type": "gpt-oss 20B F16", "model_size": 13779630336, "model_n_params": 20914757184, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": 99, "n_cpu_moe": 0, "split_mode": "layer", "main_gpu": 0, "no_kv_offload": false, "flash_attn": true, "devices": "auto", "tensor_split": "0.00", "tensor_buft_overrides": "none", "use_mmap": false, "embeddings": false, "no_op_offload": 0, "no_host": false, "n_prompt": 512, "n_gen": 0, "n_depth": 0, "test_time": "2025-10-28T18:04:31Z", "avg_ns": 347823052, "stddev_ns": 0, "avg_ts": 1472.012844, "stddev_ts": 0.000000, "samples_ns": [ 347823052 ],"samples_ts": [ 1472.01 ]}
{"build_commit": "1c1409e1", "build_number": 6865, "cpu_info": "AMD Eng Sample: 100-000001243-50_Y", "gpu_info": "Radeon 8060S Graphics", "backends": "ROCm", "model_filename": "/models/gguf/gpt-oss-20b-F16.gguf", "model_type": "gpt-oss 20B F16", "model_size": 13779630336, "model_n_params": 20914757184, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": 99, "n_cpu_moe": 0, "split_mode": "layer", "main_gpu": 0, "no_kv_offload": false, "flash_attn": true, "devices": "auto", "tensor_split": "0.00", "tensor_buft_overrides": "none", "use_mmap": false, "embeddings": false, "no_op_offload": 0, "no_host": false, "n_prompt": 0, "n_gen": 128, "n_depth": 0, "test_time": "2025-10-28T18:04:32Z", "avg_ns": 2563887565, "stddev_ns": 0, "avg_ts": 49.924186, "stddev_ts": 0.000000, "samples_ns": [ 2563887565 ],"samples_ts": [ 49.9242 ]}
{"build_commit": "1c1409e1", "build_number": 6865, "cpu_info": "AMD Eng Sample: 100-000001243-50_Y", "gpu_info": "Radeon 8060S Graphics", "backends": "ROCm", "model_filename": "/models/gguf/gpt-oss-20b-F16.gguf", "model_type": "gpt-oss 20B F16", "model_size": 13779630336, "model_n_params": 20914757184, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": 99, "n_cpu_moe": 0, "split_mode": "layer", "main_gpu": 0, "no_kv_offload": false, "flash_attn": true, "devices": "auto", "tensor_split": "0.00", "tensor_buft_overrides": "none", "use_mmap": false, "embeddings": false, "no_op_offload": 0, "no_host": false, "n_prompt": 512, "n_gen": 0, "n_depth": 1024, "test_time": "2025-10-28T18:04:34Z", "avg_ns": 368987841, "stddev_ns": 0, "avg_ts": 1387.579598, "stddev_ts": 0.000000, "samples_ns": [ 368987841 ],"samples_ts": [ 1387.58 ]}
{"build_commit": "1c1409e1", "build_number": 6865, "cpu_info": "AMD Eng Sample: 100-000001243-50_Y", "gpu_info": "Radeon 8060S Graphics", "backends": "ROCm", "model_filename": "/models/gguf/gpt-oss-20b-F16.gguf", "model_type": "gpt-oss 20B F16", "model_size": 13779630336, "model_n_params": 20914757184, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": 99, "n_cpu_moe": 0, "split_mode": "layer", "main_gpu": 0, "no_kv_offload": false, "flash_attn": true, "devices": "auto", "tensor_split": "0.00", "tensor_buft_overrides": "none", "use_mmap": false, "embeddings": false, "no_op_offload": 0, "no_host": false, "n_prompt": 0, "n_gen": 128, "n_depth": 1024, "test_time": "2025-10-28T18:04:36Z", "avg_ns": 2597940671, "stddev_ns": 0, "avg_ts": 49.269793, "stddev_ts": 0.000000, "samples_ns": [ 2597940671 ],"samples_ts": [ 49.2698 ]}
{"build_commit": "1c1409e1", "build_number": 6865, "cpu_info": "AMD Eng Sample: 100-000001243-50_Y", "gpu_info": "Radeon 8060S Graphics", "backends": "ROCm", "model_filename": "/models/gguf/gpt-oss-20b-F16.gguf", "model_type": "gpt-oss 20B F16", "model_size": 13779630336, "model_n_params": 20914757184, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": 99, "n_cpu_moe": 0, "split_mode": "layer", "main_gpu": 0, "no_kv_offload": false, "flash_attn": true, "devices": "auto", "tensor_split": "0.00", "tensor_buft_overrides": "none", "use_mmap": false, "embeddings": false, "no_op_offload": 0, "no_host": false, "n_prompt": 512, "n_gen": 0, "n_depth": 4096, "test_time": "2025-10-28T18:04:39Z", "avg_ns": 435478640, "stddev_ns": 0, "avg_ts": 1175.717826, "stddev_ts": 0.000000, "samples_ns": [ 435478640 ],"samples_ts": [ 1175.72 ]}
{"build_commit": "1c1409e1", "build_number": 6865, "cpu_info": "AMD Eng Sample: 100-000001243-50_Y", "gpu_info": "Radeon 8060S Graphics", "backends": "ROCm", "model_filename": "/models/gguf/gpt-oss-20b-F16.gguf", "model_type": "gpt-oss 20B F16", "model_size": 13779630336, "model_n_params": 20914757184, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": 99, "n_cpu_moe": 0, "split_mode": "layer", "main_gpu": 0, "no_kv_offload": false, "flash_attn": true, "devices": "auto", "tensor_split": "0.00", "tensor_buft_overrides": "none", "use_mmap": false, "embeddings": false, "no_op_offload": 0, "no_host": false, "n_prompt": 0, "n_gen": 128, "n_depth": 4096, "test_time": "2025-10-28T18:04:43Z", "avg_ns": 2658514885, "stddev_ns": 0, "avg_ts": 48.147182, "stddev_ts": 0.000000, "samples_ns": [ 2658514885 ],"samples_ts": [ 48.1472 ]}
{"build_commit": "1c1409e1", "build_number": 6865, "cpu_info": "AMD Eng Sample: 100-000001243-50_Y", "gpu_info": "Radeon 8060S Graphics", "backends": "ROCm", "model_filename": "/models/gguf/gpt-oss-20b-F16.gguf", "model_type": "gpt-oss 20B F16", "model_size": 13779630336, "model_n_params": 20914757184, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": 99, "n_cpu_moe": 0, "split_mode": "layer", "main_gpu": 0, "no_kv_offload": false, "flash_attn": true, "devices": "auto", "tensor_split": "0.00", "tensor_buft_overrides": "none", "use_mmap": false, "embeddings": false, "no_op_offload": 0, "no_host": false, "n_prompt": 512, "n_gen": 0, "n_depth": 16384, "test_time": "2025-10-28T18:04:49Z", "avg_ns": 717183120, "stddev_ns": 0, "avg_ts": 713.904142, "stddev_ts": 0.000000, "samples_ns": [ 717183120 ],"samples_ts": [ 713.904 ]}
{"build_commit": "1c1409e1", "build_number": 6865, "cpu_info": "AMD Eng Sample: 100-000001243-50_Y", "gpu_info": "Radeon 8060S Graphics", "backends": "ROCm", "model_filename": "/models/gguf/gpt-oss-20b-F16.gguf", "model_type": "gpt-oss 20B F16", "model_size": 13779630336, "model_n_params": 20914757184, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": 99, "n_cpu_moe": 0, "split_mode": "layer", "main_gpu": 0, "no_kv_offload": false, "flash_attn": true, "devices": "auto", "tensor_split": "0.00", "tensor_buft_overrides": "none", "use_mmap": false, "embeddings": false, "no_op_offload": 0, "no_host": false, "n_prompt": 0, "n_gen": 128, "n_depth": 16384, "test_time": "2025-10-28T18:05:06Z", "avg_ns": 2883875364, "stddev_ns": 0, "avg_ts": 44.384720, "stddev_ts": 0.000000, "samples_ns": [ 2883875364 ],"samples_ts": [ 44.3847 ]}
{"build_commit": "1c1409e1", "build_number": 6865, "cpu_info": "AMD Eng Sample: 100-000001243-50_Y", "gpu_info": "Radeon 8060S Graphics", "backends": "ROCm", "model_filename": "/models/gguf/gpt-oss-20b-F16.gguf", "model_type": "gpt-oss 20B F16", "model_size": 13779630336, "model_n_params": 20914757184, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": 99, "n_cpu_moe": 0, "split_mode": "layer", "main_gpu": 0, "no_kv_offload": false, "flash_attn": true, "devices": "auto", "tensor_split": "0.00", "tensor_buft_overrides": "none", "use_mmap": false, "embeddings": false, "no_op_offload": 0, "no_host": false, "n_prompt": 512, "n_gen": 0, "n_depth": 65536, "test_time": "2025-10-28T18:05:26Z", "avg_ns": 1844526619, "stddev_ns": 0, "avg_ts": 277.577995, "stddev_ts": 0.000000, "samples_ns": [ 1844526619 ],"samples_ts": [ 277.578 ]}
{"build_commit": "1c1409e1", "build_number": 6865, "cpu_info": "AMD Eng Sample: 100-000001243-50_Y", "gpu_info": "Radeon 8060S Graphics", "backends": "ROCm", "model_filename": "/models/gguf/gpt-oss-20b-F16.gguf", "model_type": "gpt-oss 20B F16", "model_size": 13779630336, "model_n_params": 20914757184, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": 99, "n_cpu_moe": 0, "split_mode": "layer", "main_gpu": 0, "no_kv_offload": false, "flash_attn": true, "devices": "auto", "tensor_split": "0.00", "tensor_buft_overrides": "none", "use_mmap": false, "embeddings": false, "no_op_offload": 0, "no_host": false, "n_prompt": 0, "n_gen": 128, "n_depth": 65536, "test_time": "2025-10-28T18:07:42Z", "avg_ns": 3682533483, "stddev_ns": 0, "avg_ts": 34.758679, "stddev_ts": 0.000000, "samples_ns": [ 3682533483 ],"samples_ts": [ 34.7587 ]}