From d082c2c9263135d48941f482ba187082ebf8da16 Mon Sep 17 00:00:00 2001
From: Junyang Lin <justinlin930319@hotmail.com>
Date: Fri, 20 Oct 2023 21:50:15 +0800
Subject: [PATCH] Update README.md

---
 README.md | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 2ba9cce..ae8ec89 100644
--- a/README.md
+++ b/README.md
@@ -683,7 +683,8 @@ We profile the GPU memory and training speed of both LoRA (LoRA (emb) refers to
 ### vLLM 
 For deployment and fast inference, we suggest using vLLM with FastChat. Install the packages first:
 ```bash
-pip install vllm fastchat
+pip install vllm
+pip install "fschat[model_worker,webui]"
 ```
 Or you can install them from source by `git clone` and `pip install -e .`. We advise you to read their documents if you meet problems in installation.