Update README.md (#10833)

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
  }' &
-```
+```