{
  "opencollection": "1.0.0",
  "info": {
    "name": "Triton Server NVIDIA Triton Server HTTP/REST CUDA Shared Memory Inference API",
    "version": "2.0"
  },
  "items": [
    {
      "info": {
        "name": "Inference",
        "type": "folder"
      },
      "items": [
        {
          "info": {
            "name": "Triton Inference Server Run Inference on a Model",
            "type": "http"
          },
          "http": {
            "method": "POST",
            "url": "http://localhost:8000/v2/models/:model_name/infer",
            "params": [
              {
                "name": "model_name",
                "value": "",
                "type": "path",
                "description": "Name of the model"
              }
            ],
            "body": {
              "type": "json",
              "data": "{}"
            }
          },
          "docs": "Submit an inference request to a model. The request specifies input tensors and requested output tensors. Supports optional parameters for sequence handling, priority, timeout, and binary data."
        },
        {
          "info": {
            "name": "Triton Inference Server Run Inference on a Specific Model Version",
            "type": "http"
          },
          "http": {
            "method": "POST",
            "url": "http://localhost:8000/v2/models/:model_name/versions/:model_version/infer",
            "params": [
              {
                "name": "model_name",
                "value": "",
                "type": "path",
                "description": "Name of the model"
              },
              {
                "name": "model_version",
                "value": "",
                "type": "path",
                "description": "Version of the model"
              }
            ],
            "body": {
              "type": "json",
              "data": "{}"
            }
          },
          "docs": "Submit an inference request to a specific version of a model."
        }
      ]
    }
  ],
  "bundled": true
}