ModelInput

Request to deploy an AI model.

AICloud ComputingGPUHPCMachine LearningSemiconductorFortune 500

Properties

Name	Type	Description
name	string
modelId	string	Hugging Face model ID.
framework	string
gpuType	string
gpuCount	integer

View JSON Schema on GitHub

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "ModelInput",
  "description": "Request to deploy an AI model.",
  "type": "object",
  "required": [
    "modelId",
    "framework",
    "gpuType"
  ],
  "properties": {
    "name": {
      "type": "string"
    },
    "modelId": {
      "type": "string",
      "description": "Hugging Face model ID."
    },
    "framework": {
      "type": "string",
      "enum": [
        "vLLM",
        "TGI",
        "TorchServe",
        "Triton"
      ]
    },
    "gpuType": {
      "type": "string"
    },
    "gpuCount": {
      "type": "integer"
    }
  }
}