[Bug] api 流式批处理bug 只能得到一个结果，然后卡死。不得不超时强制取消

### Checklist

- [x] 1. I have searched related issues but cannot get the expected help.
- [x] 2. The bug has not been fixed in the latest version.
- [x] 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.

### Describe the bug

lmdeploy 命令
```bash
python -m lmdeploy serve api_server "/mnt/d/Users/Admin/.cache//kagglehub/models/shelterw/deepseek-r1/transformers/deepseek-r1-distill-qwen-14b-awq/1" --server-name="127.0.0.1" --server-port=45001 --model-name="1" --quant-policy=8 --session-len=32768 --tp=1 --cache-max-entry-count=0.9 --backend=pytorch
```
vllm命令
```bash
python -m vllm.entrypoints.openai.api_server --model="/mnt/d/Users/Admin/.cache//kagglehub/models/shelterw/deepseek-r1/transformers/deepseek-r1-distill-qwen-14b-awq/1" --served-model-name="1" --trust-remote-code --host=127.0.0.1 --port=45001 --tensor-parallel-size=1 --gpu-memory-utilization=0.9 --max-num-seqs=256 --enforce-eager --max-model-len=16384
```
分别 使用vllm 和lmdeploy启动openai api 服务。接着使用流式并行推理。vllm功能正常。lmdeploy只有第一个正常结束，然后程序卡住，当取消以后得到第一个的结果，其余所有的都没有开始

### Reproduction

下列代码不一定能运行。我的代码内容有些复杂，让ai写了个简单的。目的都是处理流式并行 推理
```python
import openai
from typing import List

def stream_batch_inference(prompts: List[str], api_key: str, model_name: str = "1") -> List[str]:
"""
标准流式批处理请求示例
包含基础错误处理和超时机制
"""
client = openai.OpenAI(api_key=api_key)
results = ["" for _ in prompts]

try:
# 创建流式请求
response = client.chat.completions.create(
model=model_name,
messages=[[{"role": "user", "content": p}] for p in prompts],
stream=True,
timeout=30 # 整个请求超时时间
)

# 处理流式响应
for chunk in response:
if not chunk.choices:
continue

choice = chunk.choices
if choice.delta and choice.delta.content:
results[choice.index] += choice.delta.content

except openai.APITimeoutError as e:
print(f"API请求超时: {e}")
return [f"Error: Timeout - {str(e)}" for _ in prompts]

except openai.APIError as e:
print(f"API错误: {e}")
return [f"Error: API Error - {str(e)}" for _ in prompts]

return results

# 使用示例
if __name__ == "__main__":
api_key = "your-api-key" # 替换为真实API密钥
test_prompts = [
"解释量子计算的基本原理",
"用Python写个hello world程序",
"法国的首都是哪里？"
]

responses = stream_batch_inference(test_prompts, api_key)
for i, (prompt, response) in enumerate(zip(test_prompts, responses)):
print(f"Prompt {i+1}: {prompt}")
print(f"Response: {response}\n{'-'*40}")
```

### Environment

```Shell
lmdeploy check_env
sys.platform: linux
Python: 3.12.7 | packaged by Anaconda, Inc. | (main, Oct 4 2024, 13:27:36) [GCC 11.2.0]
CUDA available: True
MUSA available: False
numpy_random_seed: 2147483648
GPU 0: NVIDIA GeForce RTX 4090
CUDA_HOME: /usr/local/cuda-12.6
NVCC: Cuda compilation tools, release 12.6, V12.6.77
GCC: gcc (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0
PyTorch: 2.5.1+cu124
PyTorch compiling details: PyTorch built with:
- GCC 9.3
- C++ Version: 201703
- Intel(R) oneAPI Math Kernel Library Version 2023.1-Product Build 20230303 for Intel(R) 64 architecture applications
- Intel(R) MKL-DNN v3.5.3 (Git Hash 66f0cb9eb66affd2da3bf5f8d897376f04aae6af)
- OpenMP 201511 (a.k.a. OpenMP 4.5)
- LAPACK is enabled (usually provided by MKL)
- NNPACK is enabled
- CPU capability usage: AVX2
- CUDA Runtime 12.4
- NVCC architecture flags: -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_90,code=sm_90
- CuDNN 90.1
- Magma 2.6.1
- Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=12.4, CUDNN_VERSION=9.1.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DLIBKINETO_NOXPUPTI=ON -DUSE_FBGEMM -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=old-style-cast -Wno-missing-braces -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, TORCH_VERSION=2.5.1, USE_CUDA=ON, USE_CUDNN=ON, USE_CUSPARSELT=1, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_GLOO=ON, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, USE_ROCM_KERNEL_ASSERT=OFF,

TorchVision: 0.20.1+cu124
LMDeploy: 0.7.0.post3+c7581f6
transformers: 4.48.2
gradio: 5.13.1
fastapi: 0.115.4
pydantic: 2.8.2
triton: 3.1.0
NVIDIA Topology:
GPU0 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X N/A

Legend:

X = Self
SYS = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI)
NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node
PHB = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU)
PXB = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge)
PIX = Connection traversing at most a single PCIe bridge
NV# = Connection traversing a bonded set of # NVLinks
```

### Error traceback

```Shell

```