Checklist

• 1. I have searched related issues but cannot get the expected help.
• 2. The bug has not been fixed in the latest version.
• 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.
• 4. If the issue you raised is not a bug but a question, please raise a discussion at https://github.com/sgl-project/sglang/discussions/new/choose Otherwise, it will be closed.
• 5. Please use English, otherwise it will be closed.

Describe the bug

Input: Hello
Output, such as
Okay, the user wrote \"hello\". That's a friendly greeting. I should respond in a warm and welcoming manner. Let me make sure to keep it open-ended so they feel comfortable to ask anything they need. Maybe something like, \"Hello! How can I assist you today?\" That sounds good. Keep it simple and helpful.\n</think>\n\nHello! How can I assist you today? 😊
There is only '' but not '' in the output content.

The model runs normally and responds normally: [2025-02-17 03:38:39] INFO: 10.198.10.4:55704- "POST /v1/chat/completions HTTP/1.1" 200 OK

Reproduction

Use the dual-node 8xH100 to run the deepseek r1 671B model, send restful api requests normally and get the model's answer.

use this command:

# Launch
# node 1
docker run --gpus all \
    --shm-size 32g \
    --network=host \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --name sglang_multinode1 \
    -it \
    --rm \
    --env "HF_TOKEN=$HF_TOKEN" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server --model-path deepseek-ai/DeepSeek-R1 --tp 16 --dist-init-addr 192.168.114.10:20000 --nnodes 2 --node-rank 0 --trust-remote-code --host 0.0.0.0 --port 40000

Environment

sglang: 0.4.2.post3
flashinfer: 0.2.0.post2+cu124torch2.5     
fastapi: 0.115.8
hf_transfer: 0.1.9