Scalable Inference Serving · Schema

Model Metadata

Metadata about a deployed model in an OIP-compliant inference server. Describes the model's name, available versions, serving platform, and input/output tensor specifications.

AICNCFDeploymentInferenceKubernetesLLMMachine LearningModel ServingMLOpsScalability

Properties

Name	Type	Description
name	string	Name of the model as registered in the inference server.
versions	array	List of available model versions. May be empty if versioning is not supported.
platform	string	Backend serving platform and framework.
inputs	array	Input tensor specifications for the model.
outputs	array	Output tensor specifications for the model.

View JSON Schema on GitHub

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/scalable-inference-serving/main/json-schema/kserve-model-metadata-schema.json",
  "title": "Model Metadata",
  "description": "Metadata about a deployed model in an OIP-compliant inference server. Describes the model's name, available versions, serving platform, and input/output tensor specifications.",
  "type": "object",
  "required": ["name", "platform", "inputs", "outputs"],
  "properties": {
    "name": {
      "type": "string",
      "description": "Name of the model as registered in the inference server."
    },
    "versions": {
      "type": "array",
      "description": "List of available model versions. May be empty if versioning is not supported.",
      "items": {"type": "string"}
    },
    "platform": {
      "type": "string",
      "description": "Backend serving platform and framework.",
      "examples": [
        "tensorflow_savedmodel",
        "pytorch_libtorch",
        "sklearn_sklearn",
        "xgboost_xgboost",
        "onnxruntime_onnx",
        "ensemble",
        "vllm",
        "python"
      ]
    },
    "inputs": {
      "type": "array",
      "description": "Input tensor specifications for the model.",
      "items": {
        "$ref": "#/$defs/TensorMetadata"
      }
    },
    "outputs": {
      "type": "array",
      "description": "Output tensor specifications for the model.",
      "items": {
        "$ref": "#/$defs/TensorMetadata"
      }
    }
  },
  "$defs": {
    "TensorMetadata": {
      "type": "object",
      "title": "Tensor Metadata",
      "description": "Specification of a single input or output tensor.",
      "required": ["name", "datatype", "shape"],
      "properties": {
        "name": {
          "type": "string",
          "description": "Tensor name."
        },
        "datatype": {
          "type": "string",
          "description": "Data type (BOOL, INT32, FP32, BYTES, etc.)",
          "enum": ["BOOL", "UINT8", "UINT16", "UINT32", "UINT64", "INT8", "INT16", "INT32", "INT64", "FP16", "FP32", "FP64", "BYTES", "STRING"]
        },
        "shape": {
          "type": "array",
          "description": "Tensor shape. -1 indicates a dynamic dimension.",
          "items": {"type": "integer"},
          "example": [-1, 224, 224, 3]
        },
        "parameters": {
          "type": "object",
          "additionalProperties": true,
          "description": "Optional tensor-specific parameters."
        }
      }
    }
  }
}