worker_generate_stream "HTTP/1.1 503 Service Unavailable

Nobody has claimed this yet.

def simple_chat(use_stream=True):
messages = [
{
"role": "system",
"content": "You are ChatGLM3, a large language model trained by Zhipu.AI. Follow the user's "
"instructions carefully. Respond using markdown.",
},
{
"role": "user",
"content": "你好，请你用生动的话语给我讲一个小故事吧"
}
]
response = client.chat.completions.create(
model="chatglm3-6b",
messages=messages,
stream=use_stream,
max_tokens=256,
temperature=0.8,
presence_penalty=1.1,
top_p=0.8)
if response:
if use_stream:
for chunk in response:
print(chunk.choices[0].delta.content)
else:
content = response.choices[0].message.content
print(content)
else:
print("Error:", response.status_code)

if __name__ == "__main__":
simple_chat(use_stream=False)

I use this code to test,if use_stream=false,it runs correctly,and if use_strem=true,the running result is none,at the same time the error information on web console is :
07:59:28 | INFO | stdout | INFO: 127.0.0.1:55831 - "POST /v1/chat/completions HTTP/1.1" 200 OK
2024-01-23 07:59:31 | INFO | httpx | HTTP Request: POST http://localhost:21002/worker_generate_stream "HTTP/1.1 503 Service Unavailable"

so where is the problem?thanks!
the python version is 3.10.13,fschat version is 0.2.35

Reproduce the reported Python example with stream set to false and true, then compare the /v1/chat/completions and /worker_generate_stream request logs. Use the fschat 0.2.35 and Python 3.10.13 details from the report to trace where the streaming path returns HTTP 503; done means identifying the cause and confirming a working streaming response.

Written by the indexing model from the issue text.