Class RequestOutput

fastdeploy/engine/request.py:959–1193

The output data of a completion request to the LLM. Args: request_id: The unique ID of the request. prompt: The prompt string of the request. For encoder/decoder models, this is the decoder input prompt. prompt_token_ids: The token IDs of

class RequestOutput:
    """The output data of a completion request to the LLM.

    Args:
        request_id: The unique ID of the request.
        prompt: The prompt string of the request.
                For encoder/decoder models, this is the
                decoder input prompt.
        prompt_token_ids: The token IDs of the prompt.
                          For encoder/decoder models, this is the
                          decoder input prompt token ids.
        prompt_logprobs: The log probabilities to return per prompt token.
        outputs: The output sequences of the request.
        finished: Whether the whole request is finished.
        metrics: Metrics associated with the request.
        lora_request: The LoRA request that was used to generate the output.
        encoder_prompt: The encoder prompt string of the request.
                        None if decoder-only.
        encoder_prompt_token_ids: The token IDs of the encoder prompt.
                                  None if decoder-only.
        num_cached_tokens: The number of tokens with prefix cache hit.
        num_input_image_tokens: The number of input image tokens.
        num_input_video_tokens: The number of input video tokens.
    """

    def __init__(
        self,
        request_id: str,
        prompt: Optional[str] = None,
        prompt_token_ids: Optional[list[int]] = None,
        prompt_logprobs: Optional[PromptLogprobs] = None,
        output_type: Optional[int] = 3,
        outputs: CompletionOutput = None,
        finished: bool = False,
        metrics: Optional[RequestMetrics] = None,
        num_cached_tokens: Optional[int] = 0,
        num_input_image_tokens: Optional[int] = 0,
        num_input_video_tokens: Optional[int] = 0,
        error_code: Optional[int] = 200,
        error_msg: Optional[str] = None,
        # for internal adapter
        ic_req_data: Optional[dict] = None,
        prompt_token_ids_len: Optional[int] = 0,
        trace_carrier: dict = dict(),
    ) -> None:
        self.request_id = request_id
        self.prompt = prompt
        self.prompt_token_ids = prompt_token_ids
        self.prompt_logprobs = prompt_logprobs
        self.output_type = output_type
        self.outputs = outputs
        self.finished = finished
        self.metrics = metrics
        self.num_cached_tokens = num_cached_tokens
        self.num_input_image_tokens = num_input_image_tokens
        self.num_input_video_tokens = num_input_video_tokens
        self.error_code = error_code
        self.error_msg = error_msg