[Bug] server启动模型，调用流式返回报错

[pangr]

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.

Describe the bug

server启动模型，调用流式返回报错

`from lmdeploy.serve.openai.api_client import APIClient
from concurrent.futures import ThreadPoolExecutor

prompt = '''你是一个资深的科普大师，擅长以通俗易懂的方式介绍事物是什么吗'''

api_client = APIClient(f'http://0.0.0.0:23333')
model_name = api_client.available_models[0]

def post():
messages=[
{"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
{"role": "user", "content": prompt},
]
for item in api_client.chat_completions_v1(model=model_name,
messages=messages, temperature=0.0, top_p=1.0, stream=True):
print(item)

#for i in range(100):
with ThreadPoolExecutor(max_workers=1) as executor:
for i in range(10000):
#time.sleep(1 / qps)
future = executor.submit(post,)`

Reproduction

lmdeploy serve api_server modelpath --server-port 23333 --cache-max-entry-count 0.85 --log-level CRITICAL

Environment

lmdeploy 0.5.1
cuda12.1

Error traceback

No response

[AllentDan]

Upgrade pydantic please.