pip install langchain
pip install langchain-openai

python llm_fastapi.py

python vllm_fastapi.py

python client.py

curl https://localhost:7000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen2-4b-chat",
    "messages": [{"role": "user", "content": "你好，你是谁？"}]
  }'