Reasoning parser

[ShaoZhang0115]

Motivation

Rewrite #3202

Modifications

1. add --enable-reasoning and --reasoning-parser options for deepseek r1 series models.
2. return reasoning_content as in official api, ref: https://api-docs.deepseek.com/zh-cn/guides/reasoning_model, in both streaming and non-streaming chat completions.
   Example:

python -m sglang.launch_server --host 0.0.0.0 \
--model-path deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B \
--tp 1 --enable-reasoning --reasoning-parser deepseek-r1 

curl --location --request POST 'http: //localhost:30000/v1/chat/completions' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--data '{
    "model": "default",
    "messages": [
        {
            "role": "user",
            "content": "Calculate 1 + 3"
        }
    ],
    "stream": false
}'

Get response:

{
    "id": "53de20f7f1244195826e7b52011c37a4",
    "object": "chat.completion",
    "created": 1740507802,
    "model": "default",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "\n\n**Solution:**\n\nTo calculate \\(1 + 3\\), follow these easy steps:\n\n1. **Identify the numbers to add:**  \n   You have the number **1** and the number **3**.\n\n2. **Add the numbers together:**  \n   \\[\n   1 + 3 = 4\n   \\]\n\n3. **Final Answer:**  \n   \\[\n   \\boxed{4}\n   \\]",
                "reasoning_content": "To calculate the sum of 1 and 3, I will begin by identifying the two numbers involved in the addition. The first number is 1, and the second number is 3.\n\nNext, I will add these two numbers together. Adding 1 and 3 gives me a total of 4.\n\nTherefore, the result of 1 plus 3 is 4.\n",
                "tool_calls": null
            },
            "logprobs": null,
            "finish_reason": "stop",
            "matched_stop": 151643
        }
    ],
    "usage": {
        "prompt_tokens": 11,
        "total_tokens": 179,
        "completion_tokens": 168,
        "prompt_tokens_details": null
    }
}

Docs with be updated as soon as possible.

Checklist

• Format your code according to the Code Formatting with Pre-Commit.
• Add unit tests as outlined in the Running Unit Tests.
• Update documentation / docstrings / example tutorials as needed, according to Writing Documentation.
• Provide throughput / latency benchmark results and accuracy evaluation results as needed, according to Benchmark and Profiling and Accuracy Results.
• For reviewers: If you haven't made any contributions to this PR and are only assisting with merging the main branch, please remove yourself as a co-author when merging the PR.
• Please feel free to join our Slack channel at https://slack.sglang.ai to discuss your PR.

[shuaills]

Can we extend this to all reasoning models? Not just dpsk R1. There might be different thinking tokens.

[xihuai18]

I think different reasoning models need different parers, and I add docs for it.

[xihuai18]

• Add Docs
• Test with streaming and non-streaming cases, with truncated or non-truncated max-tokens for reasoning.

[xihuai18]

However, I can not pass my tests with --enable-torch-compile, which is confusing.