{
  "opencollection": "1.0.0",
  "info": {
    "name": "Triton Inference Server NVIDIA Triton Inference Server HTTP/REST CUDA Shared Memory Statistics API",
    "version": "2.0"
  },
  "items": [
    {
      "info": {
        "name": "Statistics",
        "type": "folder"
      },
      "items": [
        {
          "info": {
            "name": "Triton Inference Server Get Model Inference Statistics",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "http://localhost:8000/v2/models/:model_name/stats",
            "params": [
              {
                "name": "model_name",
                "value": "",
                "type": "path",
                "description": "Name of the model"
              }
            ]
          },
          "docs": "Retrieve inference statistics for a specific model including request count, execution count, and cumulative timing information. This is a Triton extension to the KServe protocol."
        },
        {
          "info": {
            "name": "Triton Inference Server Get Model Version Inference Statistics",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "http://localhost:8000/v2/models/:model_name/versions/:model_version/stats",
            "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 inference statistics for a specific version of a model."
        },
        {
          "info": {
            "name": "Triton Inference Server Get Statistics for All Models",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "http://localhost:8000/v2/models/stats"
          },
          "docs": "Retrieve inference statistics for all loaded models."
        }
      ]
    }
  ],
  "bundled": true
}