Model

A deployed AI model for inference serving.

AICloud ComputingGPUHPCMachine LearningSemiconductorFortune 500

Properties

Name	Type	Description
id	string
name	string
framework	string
status	string
endpoint	string	Inference endpoint URL.

View JSON Schema on GitHub

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "Model",
  "description": "A deployed AI model for inference serving.",
  "type": "object",
  "properties": {
    "id": {
      "type": "string"
    },
    "name": {
      "type": "string"
    },
    "framework": {
      "type": "string",
      "enum": [
        "vLLM",
        "TGI",
        "TorchServe",
        "Triton"
      ]
    },
    "status": {
      "type": "string",
      "enum": [
        "deploying",
        "serving",
        "stopped",
        "failed"
      ]
    },
    "endpoint": {
      "type": "string",
      "description": "Inference endpoint URL."
    }
  }
}