From ae3b577537ba309c247949b7c22561357d79d144 Mon Sep 17 00:00:00 2001
From: Guancheng Fu <110874468+gc-fu@users.noreply.github.com>
Date: Mon, 22 Apr 2024 11:07:10 +0800
Subject: [PATCH] Update README.md (#10833)

---
 python/llm/example/GPU/vLLM-Serving/README.md | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/python/llm/example/GPU/vLLM-Serving/README.md b/python/llm/example/GPU/vLLM-Serving/README.md
index 8afc4b51..8228a14f 100644
--- a/python/llm/example/GPU/vLLM-Serving/README.md
+++ b/python/llm/example/GPU/vLLM-Serving/README.md
@@ -136,6 +136,8 @@ Currently, for vLLM-v2, we support the following models:
 Install the dependencies for vLLM-v2 as follows:
 
 ```bash
+# This directory may change depends on where you install oneAPI-basekit
+source /opt/intel/oneapi/setvars.sh
 # First create an conda environment
 conda create -n ipex-vllm python=3.11
 conda activate ipex-vllm
@@ -200,4 +202,4 @@ Then you can access the api server as follows:
                  "max_tokens": 128,
                  "temperature": 0
  }' &
-```
\ No newline at end of file
+```