DisaggregatedParams

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/DisaggregatedParams",
  "title": "DisaggregatedParams",
  "additionalProperties": false,
  "properties": {
    "request_type": {
      "title": "Request Type",
      "type": "string",
      "description": "The type of disaggregated request."
    },
    "first_gen_tokens": {
      "default": null,
      "title": "First Gen Tokens",
      "description": "First generation tokens for continuation.",
      "items": {
        "type": "integer"
      },
      "type": "array"
    },
    "ctx_request_id": {
      "default": null,
      "title": "Ctx Request Id",
      "description": "Context request identifier.",
      "type": "integer"
    },
    "opaque_state": {
      "default": null,
      "title": "Opaque State",
      "description": "Opaque state for continuation.",
      "type": "string"
    },
    "draft_tokens": {
      "default": null,
      "title": "Draft Tokens",
      "description": "Draft tokens for speculative decoding.",
      "items": {
        "type": "integer"
      },
      "type": "array"
    },
    "multimodal_embedding_handles": {
      "default": null,
      "title": "Multimodal Embedding Handles",
      "description": "Handles for multimodal embeddings.",
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "type": "array"
    },
    "multimodal_hashes": {
      "default": null,
      "title": "Multimodal Hashes",
      "description": "Hashes for multimodal content.",
      "items": {
        "items": {
          "type": "integer"
        },
        "type": "array"
      },
      "type": "array"
    }
  },
  "required": [
    "request_type"
  ],
  "type": "object",
  "description": "Advanced parameters for disaggregated serving. Used internally."
}