diff --git a/README.md b/README.md
index 82dabd86eb8a3b7ad7b11b4b2dfad0282dbdb7c1..aa7cff6378b06ca386df1ad07c3d0b875899782c 100644
--- a/README.md
+++ b/README.md
@@ -37,8 +37,9 @@ We consider deploying deep learning inference service online to be a user-facing
 We highly recommend you to run Paddle Serving in Docker, please visit [Run in Docker](https://github.com/PaddlePaddle/Serving/blob/develop/doc/RUN_IN_DOCKER.md)
 
 ```shell
-pip install paddle-serving-client
-pip install paddle-serving-server
+pip install paddle-serving-client 
+pip install paddle-serving-server # CPU
+pip install paddle-serving-server-gpu # GPU
 ```
 
 <h2 align="center">Quick Start Example</h2>
@@ -128,6 +129,7 @@ curl -H "Content-Type:application/json" -X POST -d '{"words": "我爱北京天
 - **Description**: 
 ``` shell
 Image classification trained with Imagenet dataset. A label and corresponding probability will be returned.
+Note: This demo needs paddle-serving-server-gpu. 
 ```
 
 - **Download Servable Package**: 
diff --git a/README_CN.md b/README_CN.md
index 1858b5361a8b90f0a6517fd0dee2e63e5964d768..85a4056a0c393e3849bf5f93bf7de8973d8bc19a 100644
--- a/README_CN.md
+++ b/README_CN.md
@@ -39,7 +39,8 @@ Paddle Serving 旨在帮助深度学习开发者轻易部署在线预测服务
 
 ```shell
 pip install paddle-serving-client
-pip install paddle-serving-server
+pip install paddle-serving-server # CPU
+pip install paddle-serving-server-gpu # GPU
 ```
 
 <h2 align="center">快速启动示例</h2>
@@ -167,6 +168,7 @@ curl -H "Content-Type:application/json" -X POST -d '{"words": "我爱北京天
 - **介绍**: 
 ``` shell
 图像分类模型由Imagenet数据集训练而成，该服务会返回一个标签及其概率
+注意：本示例需要安装paddle-serving-server-gpu
 ```
 
 - **下载服务包**: