diff --git a/vllm/entrypoints/api_server.py b/vllm/entrypoints/api_server.py index f7b8d258fae4..e7af2c6db5e4 100644 --- a/vllm/entrypoints/api_server.py +++ b/vllm/entrypoints/api_server.py @@ -1,3 +1,9 @@ +""" +NOTE: This API server is used only for demonstrating usage of AsyncEngine and simple performance benchmarks. +It is not intended for production use. For production use, we recommend using our OpenAI compatible server. +We are also not going to accept PRs modifying this file, please change `vllm/entrypoints/openai/api_server.py` instead. +""" + import argparse import json from typing import AsyncGenerator