Update Doc

README.md

@@ -64,7 +64,7 @@ This chapter guides you through the installation and deployment steps. It is str
 - [Deploy Paddle Serving with Security gateway(Chinese)](doc/Serving_Auth_Docker_CN.md)
 - Deploy on more hardwares[[百度昆仑](doc/Run_On_XPU_CN.md)、[华为昇腾](doc/Run_On_NPU_CN.md)、[海光DCU](doc/Run_On_DCU_CN.md)、[Jetson](doc/Run_On_JETSON_CN.md)]
 - [Docker Images](doc/Docker_Images_EN.md)
-- [Latest Wheel packages](doc/Latest_Packages_CN.md)
+- [Download Wheel packages](doc/Latest_Packages_EN.md)
 
 > Use
 

README_CN.md

@@ -60,7 +60,7 @@ Paddle Serving依托深度学习框架PaddlePaddle旨在帮助深度学习开发
 - [部署Paddle Serving安全网关](doc/Serving_Auth_Docker_CN.md)
 - 异构硬件部署[[百度昆仑](doc/Run_On_XPU_CN.md)、[华为昇腾](doc/Run_On_NPU_CN.md)、[海光DCU](doc/Run_On_DCU_CN.md)、[Jetson](doc/Run_On_JETSON_CN.md)]
 - [Docker镜像](doc/Docker_Images_CN.md)
-- [最新Wheel开发包(English)](doc/Latest_Packages_CN.md)
+- [下载Wheel包](doc/Latest_Packages_CN.md)
 
 > 使用
 

doc/FAQ_CN.md

@@ -8,6 +8,8 @@ Failed to predict: (data_id=1 log_id=0) [det|0] Failed to postprocess: postproce
 ```
 **A:** 在服务端程序（例如 web_service.py)的postprocess函数定义中增加参数data_id，改为 def postprocess(self, input_dicts, fetch_dict, **data_id**, log_id) 即可。
 
+***
+
 ## 基础知识
 
 #### Q: Paddle Serving 、Paddle Inference、PaddleHub Serving三者的区别及联系？
@@ -40,6 +42,8 @@ Failed to predict: (data_id=1 log_id=0) [det|0] Failed to postprocess: postproce
 
 **A:** http rpc 
 
+***
+
 ## 安装问题
 
 #### Q: pip install安装whl包过程，报错信息如下：
@@ -119,6 +123,7 @@ pip install shapely==1.7.0
 方法2：
 pip install -r python/requirements.txt
 ```
+***
 
 ## 编译问题
 
@@ -144,8 +149,16 @@ make: *** [all] Error 2
 
 **A:** 运行命令安装libbz2: apt install libbz2-dev
 
+***
 ## 环境问题
 
+#### Q:  ImportError: dlopen: cannot load any more object with static TLS 
+
+**A:** 一般是用户使用Linux系统版本比较低或者Python使用的gcc版本比较低导致的，可使用以下命令检查，或者通过使用Serving或Paddle镜像安装
+```
+strings /lib/libc.so | grep GLIBC
+```
+
 #### Q：使用过程中出现CXXABI错误。
 
 这个问题出现的原因是Python使用的gcc版本和Serving所需的gcc版本对不上。对于Docker用户，推荐使用[Docker容器](https://github.com/PaddlePaddle/Serving/blob/develop/doc/Docker_Images_CN.md)，由于Docker容器内的Python版本与Serving在发布前都做过适配，这样就不会出现类似的错误。如果是其他开发环境，首先需要确保开发环境中具备GCC 8.2，如果没有gcc 8.2，参考安装方式
@@ -208,6 +221,24 @@ wget https://paddle-serving.bj.bcebos.com/others/centos_ssl.tar && \
 
   (3) Cuda10.1及更高版本需要TensorRT。安装TensorRT相关文件的脚本参考 [install_trt.sh](../tools/dockerfiles/build_scripts/install_trt.sh).
 
+***
+
+## 模型参数保存问题
+
+#### Q: 找不到'_remove_training_info'属性，详细报错信息如下：
+```
+python3 -m paddle_serving_client.convert --dirname ./ch_PP-OCRv2_det_infer/ \
+                                         --model_filename inference.pdmodel          \
+                                         --params_filename inference.pdiparams       \
+                                         --serving_server ./ppocrv2_det_serving/ \
+                                         --serving_client ./ppocrv2_det_client/ 
+ AttributeError: 'Program' object has no attribute '_remove_training_info'
+```
+
+**A:** Paddle版本低，升级Paddle版本到2.2.x及以上
+
+***
+
 ## 部署问题
 
 #### Q: GPU环境运行Serving报错，GPU count is: 0。
@@ -251,6 +282,8 @@ InvalidArgumentError: Device id must be less than GPU count, but received id is:
 #### Q: Docker中启动server IP地址 127.0.0.1 与 0.0.0.0 差异
 **A:** 您必须将容器的主进程设置为绑定到特殊的 0.0.0.0 “所有接口”地址，否则它将无法从容器外部访问。在Docker中 127.0.0.1 代表“这个容器”，而不是“这台机器”。如果您从容器建立到 127.0.0.1 的出站连接，它将返回到同一个容器；如果您将服务器绑定到 127.0.0.1，接收不到来自外部的连接。
 
+***
+
 ## 预测问题
 
 #### Q: 使用GPU第一次预测时特别慢，如何调整RPC服务的等待时间避免超时？ 
@@ -296,7 +329,7 @@ client.connect(["127.0.0.1:9393"])
 
  **A:** 参考该文档安装TensorRT: https://blog.csdn.net/hesongzefairy/article/details/105343525
 
-
+***
 
 ## 日志排查
 
@@ -321,7 +354,6 @@ GLOG_v=2 python -m paddle_serving_server.serve --model xxx_conf/ --port 9999
 ```
 
 
-
 #### Q: （GLOG_v=2下）Server端日志一切正常，但Client端始终得不到正确的预测结果
 
 **A:** 可能是配置文件有问题，检查下配置文件（is_load_tensor，fetch_type等有没有问题）
@@ -341,4 +373,3 @@ GLOG_v=2 python -m paddle_serving_server.serve --model xxx_conf/ --port 9999
 注意：可执行文件路径是C++ bin文件的路径，而不是python命令，一般为类似下面的这种/usr/local/lib/python3.6/site-packages/paddle_serving_server/serving-gpu-102-0.7.0/serving
 
 
-## 性能优化

doc/Latest_Packages_CN.md

-# Latest Wheel Packages
+# Wheel包下载
+
+(简体中文|[English](./Latest_Packages_EN.md))
 
 ## Paddle-Serving-Server (x86 CPU/GPU)
 
-Check the following table, and copy the address of hyperlink then run `pip3 install`. For example, if you want to install `paddle-serving-server-0.0.0-py3-non-any.whl`, right click the hyper link and copy the link address, the final command is `pip3 install https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server-0.0.0-py3-none-any.whl`.
+查找下面表格，拷贝链接地址，并运行 `pip3 install`。例如要安装 `paddle-serving-server-0.0.0-py3-non-any.whl`, 请右键点击链接拷贝链接地址，最终命令是`pip3 install https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server-0.0.0-py3-none-any.whl`。
 
 |                           | develop whl                                                                                                                                                              | develop bin                                                                                                                             | stable whl                                                                                                                                                               | stable bin                                                                                                                              |
 |---------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------|
@@ -14,16 +16,16 @@ Check the following table, and copy the address of hyperlink then run `pip3 inst
 | cuda10.2-cudnn8-TensorRT7 | [paddle_serving_server_gpu-0.0.0.post1028-py3-none-any.whl ](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.0.0.post102-py3-none-any.whl) | [ serving-gpu-1028-0.0.0.tar.gz]( https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-gpu-1028-0.0.0.tar.gz )                     | [paddle_serving_server_gpu-0.8.2.post1028-py3-none-any.whl ](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.8.2.post102-py3-none-any.whl) | [serving-gpu-1028-0.8.2.tar.gz]( https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-gpu-1028-0.8.2.tar.gz )                     |
 | cuda11.2-cudnn8-TensorRT8 | [paddle_serving_server_gpu-0.0.0.post112-py3-none-any.whl ](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.0.0.post112-py3-none-any.whl) | [ serving-gpu-112-0.0.0.tar.gz]( https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-gpu-112-0.0.0.tar.gz )                       | [paddle_serving_server_gpu-0.8.2.post112-py3-none-any.whl ](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.8.2.post112-py3-none-any.whl)   | [serving-gpu-112-0.8.2.tar.gz]( https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-gpu-112-0.8.2.tar.gz )                       |
 
-### Binary Package
-for most users, we do not need to read this section. But if you deploy your Paddle Serving on a machine without network, you will encounter a problem that the binary executable tar file cannot be downloaded. Therefore, here we give you all the download links for various environment.
+### 二进制包（Binary Package）
+大多数用户不会用到此章节。但是如果你在无网络的环境下部署Paddle Serving，在首次启动Serving时，无法下载二进制tar文件。因此，提供多种环境二进制包的下载链接，下载后传到无网络环境的指定目录下，即可使用。
 
-### How to setup SERVING_BIN offline?
+### 如何离线设置SERVING_BIN?
 
-- download the serving server whl package and bin package, and make sure they are for the same environment
-- download the serving client whl and serving app whl, pay attention to the Python version.
-- `pip install ` the serving and `tar xf ` the binary package, then `export SERVING_BIN=$PWD/serving-gpu-cuda11-0.0.0/serving` (take Cuda 11 as the example)
+- 下载Serving Server Wheel包和二进制tar包，确保它们与环境是一致的
+- 下载Serving Client Wheel包和Serving App wheel包, 同时注意Python版本要一致.
+- `pip install ` 所有Wheel包 and `tar xf ` 二进制tar包, 然后`export SERVING_BIN=$PWD/serving-gpu-cuda11-0.0.0/serving` (以Cuda 11为例)
 
-## paddle-serving-client 
+## paddle-serving-client Wheel包
 
 |  | develop whl                                                                                                                                      | stable whl                                                                                                                                        |
 |-----------------------|--------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------|
@@ -31,20 +33,21 @@ for most users, we do not need to read this section. But if you deploy your Padd
 | Python3.7             | [paddle_serving_client-0.0.0-cp37-none-any.whl](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-0.0.0-cp37-none-any.whl) | [paddle_serving_client-0.8.2-cp37-none-any.whl](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-0.8.2-cp37-none-any.whl)  |
 | Python3.8             | [paddle_serving_client-0.0.0-cp38-none-any.whl](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-0.0.0-cp38-none-any.whl) | [paddle_serving_client-0.8.2-cp38-none-any.whl](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-0.8.2-cp38-none-any.whl)  |
 | Python3.9             | [paddle_serving_client-0.0.0-cp39-none-any.whl](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-0.0.0-cp39-none-any.whl) | [paddle_serving_client-0.8.2-cp39-none-any.whl](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-0.8.2-cp38-none-any.whl)  |
-## paddle-serving-app
+
+## paddle-serving-app Wheel包
 
 |         | develop whl                                                                                                                              | stable whl                                                                                                                                  |
 |---------|------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------|
 | Python3 | [paddle_serving_app-0.0.0-py3-none-any.whl](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_app-0.0.0-py3-none-any.whl) | [ paddle_serving_app-0.8.2-py3-none-any.whl ]( https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_app-0.8.2-py3-none-any.whl) |
 
 
-## Baidu Kunlun user
-for kunlun user who uses arm-xpu or x86-xpu can download the wheel packages as follows. Users should use the xpu-beta docker [DOCKER IMAGES](./Docker_Images_CN.md) 
-**We only support Python 3.6 for Kunlun Users.**
+## 百度昆仑芯片
+对于使用百度昆仑芯片的用户， 通过以下方式下载arm-xpu 或 x86-xpu Wheel包。选择 xpu-beta docker [DOCKER镜像](./Docker_Images_CN.md) 
+**昆仑环境仅支持python36**
 
-### Wheel Package Links
+### Wheel包链接
 
-for arm kunlun user
+适用ARM CPU环境的昆仑Wheel包：
 ```
 # paddle-serving-server
 https://paddle-serving.bj.bcebos.com/whl/xpu/arm/paddle_serving_server_xpu-0.0.0.post2-py3-none-any.whl
@@ -57,7 +60,7 @@ https://paddle-serving.bj.bcebos.com/whl/xpu/arm/paddle_serving_app-0.0.0-py3-no
 https://paddle-serving.bj.bcebos.com/bin/serving-xpu-aarch64-0.0.0.tar.gz
 ```
  
-for x86 kunlun user
+适用于x86 CPU环境的昆仑Wheel包：
 ``` 
 https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_xpu-0.8.2.post2-py3-none-any.whl
 

doc/Latest_Packages_EN.md

+# Download Wheel Packages
+
+(English|[简体中文](./Latest_Packages_CN.md))
+
+## Paddle-Serving-Server (x86 CPU/GPU)
+
+Check the following table, and copy the address of hyperlink then run `pip3 install`. For example, if you want to install `paddle-serving-server-0.0.0-py3-non-any.whl`, right click the hyper link and copy the link address, the final command is `pip3 install https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server-0.0.0-py3-none-any.whl`.
+
+|                           | develop whl                                                                                                                                                              | develop bin                                                                                                                             | stable whl                                                                                                                                                               | stable bin                                                                                                                              |
+|---------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------|
+| cpu-avx-mkl               | [paddle_serving_server-0.0.0-py3-none-any.whl ](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server-0.0.0-py3-none-any.whl)                          | [serving-cpu-avx-mkl-0.0.0.tar.gz](https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-cpu-avx-mkl-0.0.0.tar.gz)                  | [paddle_serving_server-0.8.2-py3-none-any.whl ](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server-0.8.2-py3-none-any.whl)                          | [serving-cpu-avx-mkl-0.8.2.tar.gz](https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-cpu-avx-mkl-0.8.2.tar.gz)                  |
+| cpu-avx-openblas          | [paddle_serving_server-0.0.0-py3-none-any.whl ](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server-0.0.0-py3-none-any.whl)                          | [serving-cpu-avx-openblas-0.0.0.tar.gz](https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-cpu-avx-openblas-0.0.0.tar.gz)        | [paddle_serving_server-0.8.2-py3-none-any.whl ](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server-0.8.2-py3-none-any.whl)                          | [serving-cpu-avx-openblas-0.8.2.tar.gz](https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-cpu-avx-openblas-0.8.2.tar.gz)        |
+| cpu-noavx-openblas        | [paddle_serving_server-0.0.0-py3-none-any.whl ](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server-0.0.0-py3-none-any.whl)                          | [ serving-cpu-noavx-openblas-0.0.0.tar.gz ]( https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-cpu-noavx-openblas-0.0.0.tar.gz) | [paddle_serving_server-0.8.2-py3-none-any.whl ](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server-0.8.2-py3-none-any.whl)                          | [serving-cpu-noavx-openblas-0.8.2.tar.gz]( https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-cpu-noavx-openblas-0.8.2.tar.gz) |
+| cuda10.1-cudnn7-TensorRT6 | [paddle_serving_server_gpu-0.0.0.post101-py3-none-any.whl ](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.0.0.post101-py3-none-any.whl)  | [serving-gpu-101-0.0.0.tar.gz](https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-gpu-101-0.0.0.tar.gz)                          | [paddle_serving_server_gpu-0.8.2.post101-py3-none-any.whl ](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.8.2.post101-py3-none-any.whl)  | [serving-gpu-101-0.8.2.tar.gz](https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-gpu-101-0.8.2.tar.gz)                          |
+| cuda10.2-cudnn7-TensorRT6 | [paddle_serving_server_gpu-0.0.0.post102-py3-none-any.whl ](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.0.0.post102-py3-none-any.whl)  | [serving-gpu-102-0.0.0.tar.gz](https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-gpu-102-0.0.0.tar.gz)                          | [paddle_serving_server_gpu-0.8.2.post102-py3-none-any.whl ](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.8.2.post102-py3-none-any.whl)  | [serving-gpu-102-0.8.2.tar.gz](https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-gpu-102-0.8.2.tar.gz)                          |
+| cuda10.2-cudnn8-TensorRT7 | [paddle_serving_server_gpu-0.0.0.post1028-py3-none-any.whl ](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.0.0.post102-py3-none-any.whl) | [ serving-gpu-1028-0.0.0.tar.gz]( https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-gpu-1028-0.0.0.tar.gz )                     | [paddle_serving_server_gpu-0.8.2.post1028-py3-none-any.whl ](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.8.2.post102-py3-none-any.whl) | [serving-gpu-1028-0.8.2.tar.gz]( https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-gpu-1028-0.8.2.tar.gz )                     |
+| cuda11.2-cudnn8-TensorRT8 | [paddle_serving_server_gpu-0.0.0.post112-py3-none-any.whl ](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.0.0.post112-py3-none-any.whl) | [ serving-gpu-112-0.0.0.tar.gz]( https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-gpu-112-0.0.0.tar.gz )                       | [paddle_serving_server_gpu-0.8.2.post112-py3-none-any.whl ](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.8.2.post112-py3-none-any.whl)   | [serving-gpu-112-0.8.2.tar.gz]( https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-gpu-112-0.8.2.tar.gz )                       |
+
+### Binary Package
+for most users, we do not need to read this section. But if you deploy your Paddle Serving on a machine without network, you will encounter a problem that the binary executable tar file cannot be downloaded. Therefore, here we give you all the download links for various environment.
+
+### How to setup SERVING_BIN offline?
+
+- download the serving server whl package and bin package, and make sure they are for the same environment
+- download the serving client whl and serving app whl, pay attention to the Python version.
+- `pip install ` the serving and `tar xf ` the binary package, then `export SERVING_BIN=$PWD/serving-gpu-cuda11-0.0.0/serving` (take Cuda 11 as the example)
+
+## paddle-serving-client 
+
+|  | develop whl                                                                                                                                      | stable whl                                                                                                                                        |
+|-----------------------|--------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------|
+| Python3.6             | [paddle_serving_client-0.0.0-cp36-none-any.whl](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-0.0.0-cp36-none-any.whl) | [paddle_serving_client-0.8.2-cp36-none-any.whl](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-0.8.2-cp36-none-any.whl)  |
+| Python3.7             | [paddle_serving_client-0.0.0-cp37-none-any.whl](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-0.0.0-cp37-none-any.whl) | [paddle_serving_client-0.8.2-cp37-none-any.whl](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-0.8.2-cp37-none-any.whl)  |
+| Python3.8             | [paddle_serving_client-0.0.0-cp38-none-any.whl](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-0.0.0-cp38-none-any.whl) | [paddle_serving_client-0.8.2-cp38-none-any.whl](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-0.8.2-cp38-none-any.whl)  |
+| Python3.9             | [paddle_serving_client-0.0.0-cp39-none-any.whl](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-0.0.0-cp39-none-any.whl) | [paddle_serving_client-0.8.2-cp39-none-any.whl](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-0.8.2-cp38-none-any.whl)  |
+## paddle-serving-app
+
+|         | develop whl                                                                                                                              | stable whl                                                                                                                                  |
+|---------|------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------|
+| Python3 | [paddle_serving_app-0.0.0-py3-none-any.whl](https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_app-0.0.0-py3-none-any.whl) | [ paddle_serving_app-0.8.2-py3-none-any.whl ]( https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_app-0.8.2-py3-none-any.whl) |
+
+
+## Baidu Kunlun user
+for kunlun user who uses arm-xpu or x86-xpu can download the wheel packages as follows. Users should use the xpu-beta docker [DOCKER IMAGES](./Docker_Images_CN.md) 
+**We only support Python 3.6 for Kunlun Users.**
+
+### Wheel Package Links
+
+for arm kunlun user
+```
+# paddle-serving-server
+https://paddle-serving.bj.bcebos.com/whl/xpu/arm/paddle_serving_server_xpu-0.0.0.post2-py3-none-any.whl
+# paddle-serving-client
+https://paddle-serving.bj.bcebos.com/whl/xpu/arm/paddle_serving_client-0.0.0-cp36-none-any.whl
+# paddle-serving-app
+https://paddle-serving.bj.bcebos.com/whl/xpu/arm/paddle_serving_app-0.0.0-py3-none-any.whl
+
+# SERVING BIN
+https://paddle-serving.bj.bcebos.com/bin/serving-xpu-aarch64-0.0.0.tar.gz
+```
+ 
+for x86 kunlun user
+``` 
+https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_xpu-0.8.2.post2-py3-none-any.whl
+
+```
+
+