TensorRT-LLMs/tests/unittest/api_stability/references_committed/request_output.yaml

methods:
  aresult:
    parameters: {}
    return_annotation: tensorrt_llm.executor.result.GenerationResult
  result:
    parameters:
      timeout:
        annotation: Optional[float]
        default: None
    return_annotation: tensorrt_llm.executor.result.GenerationResult
properties:
  request_id:
    annotation: int
    default: inspect._empty
  prompt:
    annotation: Optional[str]
    default: inspect._empty
  prompt_token_ids:
    annotation: List[int]
    default: inspect._empty
  outputs:
    annotation: List[tensorrt_llm.executor.result.CompletionOutput]
    default: inspect._empty
  context_logits:
    annotation: Optional[torch.Tensor]
    default: inspect._empty
  finished:
    annotation: bool
    default: inspect._empty
  mm_embedding_handle:
    annotation: Optional[Dict[str, Any]]
    default: inspect._empty