Scalable Inference Serving · Schema

ServerMetadataResponse

Server metadata including name, version, and supported extensions.

AICNCFDeploymentInferenceKubernetesLLMMachine LearningModel ServingMLOpsScalability

Properties

Name Type Description
name string Server implementation name (e.g., triton, kserve, bentoml).
version string Server version string.
extensions array List of protocol extensions supported by the server.
View JSON Schema on GitHub

JSON Schema

scalable-inference-serving-servermetadataresponse-schema.json Raw ↑ 
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/ServerMetadataResponse",
  "title": "ServerMetadataResponse",
  "type": "object",
  "description": "Server metadata including name, version, and supported extensions.",
  "required": [
    "name",
    "version",
    "extensions"
  ],
  "properties": {
    "name": {
      "type": "string",
      "description": "Server implementation name (e.g., triton, kserve, bentoml).",
      "example": "triton"
    },
    "version": {
      "type": "string",
      "description": "Server version string.",
      "example": "2.30.0"
    },
    "extensions": {
      "type": "array",
      "description": "List of protocol extensions supported by the server.",
      "items": {
        "type": "string"
      },
      "example": [
        "binary_tensor_data",
        "classification"
      ]
    }
  }
}