推理输出

vLLM 为推理模型提供支持，例如 DeepSeek R1，这些模型旨在生成包含推理步骤和最终结论的输出。

推理模型在其输出中返回一个额外的 reasoning_content 字段，其中包含导致最终结论的推理步骤。此字段在其他模型的输出中不存在。

支持的模型

vLLM 目前支持以下推理模型

• DeepSeek R1 系列 (deepseek_r1，它查找 <think> ... </think>)

快速入门

要使用推理模型，您需要在向聊天完成端点发出请求时指定 --enable-reasoning 和 --reasoning-parser 标志。--reasoning-parser 标志指定用于从模型输出中提取推理内容的推理解析器。

vllm serve deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B \
    --enable-reasoning --reasoning-parser deepseek_r1

接下来，向应该在响应中返回推理内容的模型发出请求。

from openai import OpenAI

# Modify OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "https://127.0.0.1:8000/v1"

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)

models = client.models.list()
model = models.data[0].id

# Round 1
messages = [{"role": "user", "content": "9.11 and 9.8, which is greater?"}]
response = client.chat.completions.create(model=model, messages=messages)

reasoning_content = response.choices[0].message.reasoning_content
content = response.choices[0].message.content

print("reasoning_content:", reasoning_content)
print("content:", content)

reasoning_content 字段包含导致最终结论的推理步骤，而 content 字段包含最终结论。

流式聊天完成

推理模型也支持流式聊天完成。reasoning_content 字段在聊天完成响应块的 delta 字段中可用。

{
    "id": "chatcmpl-123",
    "object": "chat.completion.chunk",
    "created": 1694268190,
    "model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
    "system_fingerprint": "fp_44709d6fcb",
    "choices": [
        {
            "index": 0,
            "delta": {
                "role": "assistant",
                "reasoning_content": "is",
            },
            "logprobs": null,
            "finish_reason": null
        }
    ]
}

请注意，它与 OpenAI Python 客户端库不兼容。您可以使用 requests 库发出流式请求。

如何支持新的推理模型

您可以添加一个新的 ReasoningParser，类似于 vllm/entrypoints/openai/reasoning_parsers/deepseek_r1_reasoning_parser.py。

# import the required packages

from vllm.entrypoints.openai.reasoning_parsers.abs_reasoning_parsers import (
    ReasoningParser, ReasoningParserManager)
from vllm.entrypoints.openai.protocol import (ChatCompletionRequest,
                                              DeltaMessage)

# define a reasoning parser and register it to vllm
# the name list in register_module can be used
# in --reasoning-parser.
@ReasoningParserManager.register_module(["example"])
class ExampleParser(ReasoningParser):
    def __init__(self, tokenizer: AnyTokenizer):
        super().__init__(tokenizer)

    def extract_reasoning_content_streaming(
        self,
        previous_text: str,
        current_text: str,
        delta_text: str,
        previous_token_ids: Sequence[int],
        current_token_ids: Sequence[int],
        delta_token_ids: Sequence[int],
    ) -> Union[DeltaMessage, None]:
        """
        Instance method that should be implemented for extracting reasoning
        from an incomplete response; for use when handling reasoning calls and
        streaming. Has to be an instance method because  it requires state -
        the current tokens/diffs, but also the information about what has
        previously been parsed and extracted (see constructor)
        """

    def extract_reasoning_content(
            self, model_output: str, request: ChatCompletionRequest
    ) -> Tuple[Optional[str], Optional[str]]:
        """
        Extract reasoning content from a complete model-generated string.

        Used for non-streaming responses where we have the entire model response
        available before sending to the client.

        Parameters:
        model_output: str
            The model-generated string to extract reasoning content from.

        request: ChatCompletionRequest
            The request object that was used to generate the model_output.

        Returns:
        Tuple[Optional[str], Optional[str]]
            A tuple containing the reasoning content and the content.
        """

定义推理解析器后，您可以通过在向聊天完成端点发出请求时指定 --reasoning-parser 标志来使用它。

vllm serve <model_tag> \
    --enable-reasoning --reasoning-parser example

局限性

• 推理内容仅适用于在线服务的聊天完成端点 (/v1/chat/completions)。

• 它与 structured_outputs 和 tool_calling 功能不兼容。

• 推理内容并非适用于所有模型。请查看模型的文档以了解其是否支持推理。