Send a chat completion request to verify the server is working:
# List available models
curl http://localhost:8000/api/v1/models
# Chat with a model (replace MODEL_NAME)
curl -X POST http://localhost:8000/api/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{"model": "MODEL_NAME", "messages": [{"role": "user", "content": "Hello!"}]}'