{ "opencollection": "1.0.0", "info": { "name": "Triton Inference Server NVIDIA Triton Inference Server HTTP/REST CUDA Shared Memory Model Metadata API", "version": "2.0" }, "items": [ { "info": { "name": "Model Metadata", "type": "folder" }, "items": [ { "info": { "name": "Triton Inference Server Get Model Metadata", "type": "http" }, "http": { "method": "GET", "url": "http://localhost:8000/v2/models/:model_name", "params": [ { "name": "model_name", "value": "", "type": "path", "description": "Name of the model" } ] }, "docs": "Retrieve metadata about a specific model including its name, versions, platform, and input/output tensor information." }, { "info": { "name": "Triton Inference Server Get Model Version Metadata", "type": "http" }, "http": { "method": "GET", "url": "http://localhost:8000/v2/models/:model_name/versions/:model_version", "params": [ { "name": "model_name", "value": "", "type": "path", "description": "Name of the model" }, { "name": "model_version", "value": "", "type": "path", "description": "Version of the model" } ] }, "docs": "Retrieve metadata about a specific version of a model." }, { "info": { "name": "Triton Inference Server Get Model Configuration", "type": "http" }, "http": { "method": "GET", "url": "http://localhost:8000/v2/models/:model_name/config", "params": [ { "name": "model_name", "value": "", "type": "path", "description": "Name of the model" } ] }, "docs": "Retrieve the configuration of a specific model as defined in the model repository. This is a Triton extension to the KServe protocol." }, { "info": { "name": "Triton Inference Server Get Model Version Configuration", "type": "http" }, "http": { "method": "GET", "url": "http://localhost:8000/v2/models/:model_name/versions/:model_version/config", "params": [ { "name": "model_name", "value": "", "type": "path", "description": "Name of the model" }, { "name": "model_version", "value": "", "type": "path", "description": "Version of the model" } ] }, "docs": "Retrieve the configuration of a specific version of a model." } ] } ], "bundled": true }