From 86fd8bb0ac9a836e55b5075d8416bd067af9e7b2 Mon Sep 17 00:00:00 2001 From: Simon Mo Date: Sun, 18 Feb 2024 21:36:19 -0800 Subject: [PATCH] Add warning to prevent changes to benchmark api server (#2858) --- vllm/entrypoints/api_server.py | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/vllm/entrypoints/api_server.py b/vllm/entrypoints/api_server.py index f7b8d258..e7af2c6d 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