推理输出¶
vLLM 支持像 DeepSeek R1 这样的推理模型，它们被设计用来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 字段，其中包含导致最终结论的推理步骤。其他模型的输出中不存在此字段。
警告
reasoning 以前称为 reasoning_content。目前，reasoning_content 仍可正常工作。但是，我们建议您迁移到 reasoning，以防 reasoning_content 在将来被移除。
支持的模型¶
vLLM 目前支持以下推理模型
| 模型系列 | 解析器名称 | 结构化输出支持 | 工具调用 |
|---|---|---|---|
| DeepSeek R1 系列 | deepseek_r1 | json, regex | ❌ |
| DeepSeek-V3.1 | deepseek_v3 | json, regex | ❌ |
| ERNIE-4.5-VL 系列 | ernie45 | json, regex | ❌ |
| ERNIE-4.5-21B-A3B-Thinking | ernie45 | json, regex | ✅ |
| GLM-4.5 系列 | glm45 | json, regex | ✅ |
| Holo2 系列 | holo2 | json, regex | ✅ |
| Hunyuan A13B 系列 | hunyuan_a13b | json, regex | ✅ |
| IBM Granite 3.2 语言模型 | granite | ❌ | ❌ |
| MiniMax-M2 | minimax_m2_append_think | json, regex | ✅ |
| Qwen3 系列 | qwen3 | json, regex | ✅ |
| QwQ-32B | deepseek_r1 | json, regex | ✅ |
注意
IBM Granite 3.2 和 DeepSeek-V3.1 的推理默认禁用；要启用它，您还必须在 chat_template_kwargs 中传递 thinking=True。Qwen3 系列的推理功能默认启用。要禁用它，您必须在 chat_template_kwargs 中传递 enable_thinking=False。DeepSeek-V3.1 工具调用在非思考模式下受支持。Holo2 的推理默认启用。要禁用它，您还必须在 chat_template_kwargs 中传递 thinking=False。
快速入门¶
要使用推理模型，您需要在向聊天补全端点发出请求时指定 --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。
接下来，向应该在响应中返回推理内容的模型发出请求。
代码
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://: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?"}]
# For granite, add: `extra_body={"chat_template_kwargs": {"thinking": True}}`
# For Qwen3 series, if you want to disable thinking in reasoning mode, add:
# extra_body={"chat_template_kwargs": {"enable_thinking": False}}
response = client.chat.completions.create(model=model, messages=messages)
reasoning = response.choices[0].message.reasoning
content = response.choices[0].message.content
print("reasoning:", reasoning)
print("content:", content)
reasoning 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。
流式聊天补全¶
流式聊天补全也支持推理模型。reasoning 字段在 聊天补全响应块 的 delta 字段中可用。
Json
{
"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": "is",
},
"logprobs": null,
"finish_reason": null
}
]
}
OpenAI Python 客户端库不正式支持流式输出的 reasoning 属性。但该客户端支持响应中的额外属性。您可以使用 hasattr 检查响应中是否存在 reasoning 属性。例如
代码
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://:8000/v1"
client = OpenAI(
api_key=openai_api_key,
base_url=openai_api_base,
)
models = client.models.list()
model = models.data[0].id
messages = [{"role": "user", "content": "9.11 and 9.8, which is greater?"}]
# For granite, add: `extra_body={"chat_template_kwargs": {"thinking": True}}`
# For Qwen3 series, if you want to disable thinking in reasoning mode, add:
# extra_body={"chat_template_kwargs": {"enable_thinking": False}}
stream = client.chat.completions.create(
model=model,
messages=messages,
stream=True,
)
print("client: Start streaming chat completions...")
printed_reasoning = False
printed_content = False
for chunk in stream:
# Safely extract reasoning and content from delta,
# defaulting to None if attributes don't exist or are empty strings
reasoning = (
getattr(chunk.choices[0].delta, "reasoning", None) or None
)
content = getattr(chunk.choices[0].delta, "content", None) or None
if reasoning is not None:
if not printed_reasoning:
printed_reasoning = True
print("reasoning:", end="", flush=True)
print(reasoning, end="", flush=True)
elif content is not None:
if not printed_content:
printed_content = True
print("\ncontent:", end="", flush=True)
# Extract and print the content
print(content, end="", flush=True)
请记住，在访问 reasoning 之前，请检查它是否存在于响应中。您可以查看 示例。
工具调用¶
当同时启用工具调用和推理解析器时，推理内容也可用。此外，工具调用仅从 content 字段解析函数，不从 reasoning 中解析。
代码
from openai import OpenAI
client = OpenAI(base_url="https://:8000/v1", api_key="dummy")
tools = [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {"type": "string", "description": "City and state, e.g., 'San Francisco, CA'"},
"unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
},
"required": ["location", "unit"],
}
},
}
]
response = client.chat.completions.create(
model=client.models.list().data[0].id,
messages=[{"role": "user", "content": "What's the weather like in San Francisco?"}],
tools=tools,
tool_choice="auto",
)
print(response)
tool_call = response.choices[0].message.tool_calls[0].function
print(f"reasoning: {response.choices[0].message.reasoning}")
print(f"Function called: {tool_call.name}")
print(f"Arguments: {tool_call.arguments}")
更多示例，请参阅 examples/online_serving/openai_chat_completion_tool_calls_with_reasoning.py.
限制¶
- 推理内容仅适用于在线服务的聊天补全端点 (
/v1/chat/completions)。
如何支持新的推理模型¶
您可以添加一个新的 ReasoningParser，类似于 vllm/reasoning/deepseek_r1_reasoning_parser.py。
代码
# import the required packages
from vllm.reasoning 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.
class ExampleParser(ReasoningParser):
def __init__(self, tokenizer: TokenizerLike):
super().__init__(tokenizer)
def extract_reasoning_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],
) -> 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(
self,
model_output: str,
request: ChatCompletionRequest | ResponsesRequest,
) -> tuple[str | None, str | None]:
"""
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.
"""
# Register the reasoning parser
ReasoningParserManager.register_lazy_module(
name="example",
module_path="vllm.reasoning.example_reasoning_parser",
class_name="ExampleParser",
)
此外，要启用结构化输出，您需要创建一个新的 Reasoner，类似于 vllm/reasoning/deepseek_r1_reasoning_parser.py 中的示例。
代码
@dataclass
class DeepSeekReasoner(Reasoner):
"""
Reasoner for DeepSeek R series models.
"""
start_token_id: int
end_token_id: int
start_token: str = "<think>"
end_token: str = "</think>"
@classmethod
def from_tokenizer(cls, tokenizer: PreTrainedTokenizer) -> Reasoner:
return cls(
start_token_id=tokenizer.encode("<think>", add_special_tokens=False)[0],
end_token_id=tokenizer.encode("</think>", add_special_tokens=False)[0],
)
def is_reasoning_end(self, input_ids: list[int]) -> bool:
return self.end_token_id in input_ids
def is_reasoning_end_streaming(self, input_ids: list[int], delta_ids: list[int]) -> bool:
return self.end_token_id in delta_token_ids
...
像 xgrammar 这样的结构化输出引擎将使用 end_token_id 来检查推理内容是否存在于模型输出中，并在存在时跳过结构化输出。
最后，您可以通过使用 --reasoning-parser 标志来为模型启用推理。