[Bug]: vllm部署后，用官方的例子调用报错openai.BadRequestError: Error code: 400 - {'object': 'error', 'message': "name 'Extension' is not defined", 'type': 'BadRequestError', 'param': None, 'code': 400}

[1gst]

Model Series

Qwen2.5

What are the models used?

Qwen2.5-14b-Instruct

What is the scenario where the problem happened?

vllm版本是0.6.2

Is this badcase known and can it be solved using avaiable techniques?

• I have followed the GitHub README.
• I have checked the Qwen documentation and cannot find a solution there.
• I have checked the documentation of the related framework and cannot find useful information.
• I have searched the issues and there is not a similar one.

Information about environment

Ubuntu20.04.6TLS
CPU：2AMD Milan 7543 32核 2.8GHz
内存：1TB
硬盘：2SATA SSD 3.84TB
网卡：双口千兆1+双口万兆1
显卡：4*A100_SXM4_40GB NV-Link
cuda 12.2

Description

按照官方的例子进行的操作
pip install vllm
vllm serve Qwen/Qwen2.5-7B-Instruct
然后运行代码：

from openai import OpenAI
# Set OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)

chat_response = client.chat.completions.create(
    model="Qwen/Qwen2.5-7B-Instruct",
    messages=[
        {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
        {"role": "user", "content": "Tell me something about large language models."},
    ],
    temperature=0.7,
    top_p=0.8,
    max_tokens=512,
    extra_body={
        "repetition_penalty": 1.05,
    },
)
print("Chat response:", chat_response)

能够确保的是成功部署了模型，并且能够调到模型接口，部署日志也会报这个错误。

[1gst]

[jklj077]

the error appeared to be raised by transformers but that's unusual. what's your transformers version?