[BUG] <title> No heartbeat received from MQLLMEngine

[hulk-zhk]

是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this?

• 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions

该问题是否在FAQ中有解答？ | Is there an existing answer for this in FAQ?

• 我已经搜索过FAQ | I have searched FAQ

当前行为 | Current Behavior

PyTorch version: 2.4.0+cu121
Python version: 3.10.12
启动模型服务：
python3 -m vllm.entrypoints.openai.api_server --host 0.0.0.0
--port 10023 --seed 1024
--served-model qwen1.5-4b
--model "/home/work/ssd1/Qwen1.5-4B-Chat" --trust-remote-code
--tokenizer-mode slow --max-model-len 128
--dtype float16
进行模型推理：
curl http://127.0.0.1:10023/v1/completions
-H "Content-Type: application/json"
-d '{
"model":"qwen1.5-4b", "max_tokens":64, "seed":0, "top_k":1, "top_p":0.8, "temperature":0.3,
"prompt": "谈谈你对大模型的理解"
}'
报错信息：
No heartbeat received from MQLLMEngine

期望行为 | Expected Behavior

No response

复现方法 | Steps To Reproduce

No response

运行环境 | Environment

- OS:
- Python:
- Transformers:
- PyTorch:
- CUDA (`python -c 'import torch; print(torch.version.cuda)'`):

备注 | Anything else?

No response

[github-actions]

This issue has been automatically marked as inactive due to lack of recent activity. Should you believe it remains unresolved and warrants attention, kindly leave a comment on this thread.
此问题由于长期未有新进展而被系统自动标记为不活跃。如果您认为它仍有待解决，请在此帖下方留言以补充信息。