From 61c67af3866b7ae8af388698faa875974d270689 Mon Sep 17 00:00:00 2001
From: Guancheng Fu <110874468+gc-fu@users.noreply.github.com>
Date: Mon, 22 Apr 2024 09:02:48 +0800
Subject: [PATCH] Fix vLLM-v2 install instructions(#10822)

---
 python/llm/example/GPU/vLLM-Serving/README.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/python/llm/example/GPU/vLLM-Serving/README.md b/python/llm/example/GPU/vLLM-Serving/README.md
index 8d84a130..8afc4b51 100644
--- a/python/llm/example/GPU/vLLM-Serving/README.md
+++ b/python/llm/example/GPU/vLLM-Serving/README.md
@@ -34,6 +34,8 @@ sycl-ls
 To run vLLM continuous batching on Intel GPUs, install the dependencies 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