diff --git a/doc/Install_CN.md b/doc/Install_CN.md index acff887f2..6584016c3 100644 --- a/doc/Install_CN.md +++ b/doc/Install_CN.md @@ -4,10 +4,16 @@ - [1.使用开发镜像](#1) - [Serving 开发镜像](#1.1) + - [CPU 镜像](#1.1.1) + - [GPU 镜像](#1.1.2) + - [ARM & XPU 镜像](#1.1.3) - [Paddle 开发镜像](#1.2) + - [CPU 镜像](#1.2.1) + - [GPU 镜像](#1.2.2) - [2.安装 Wheel 包](#2) - [在线安装](#2.1) - [离线安装](#2.2) + - [ARM & XPU 包安装](#2.3) - [3.环境检查](#3) @@ -33,33 +39,52 @@ | CUDA10.2 + cuDNN 7 | 0.9.0-cuda10.2-cudnn7-devel | Ubuntu 16 | 2.3.0-gpu-cuda10.2-cudnn7 | Ubuntu 18 | CUDA10.2 + cuDNN 8 | 0.9.0-cuda10.2-cudnn8-devel | Ubuntu 16 | 无 | Ubuntu 18 | | CUDA11.2 + cuDNN 8 | 0.9.0-cuda11.2-cudnn8-devel | Ubuntu 16 | 2.3.0-gpu-cuda11.2-cudnn8 | Ubuntu 18 | +| ARM + XPU | xpu-arm | CentOS 8.3 | 无 | 无 | 对于**Windows 10 用户**，请参考文档[Windows平台使用Paddle Serving指导](Windows_Tutorial_CN.md)。 - ### 1.1 Serving开发镜像（CPU/GPU 2选1） + + + **CPU：** ``` # 启动 CPU Docker docker pull registry.baidubce.com/paddlepaddle/serving:0.9.0-devel -docker run -p 9292:9292 --name test -dit registry.baidubce.com/paddlepaddle/serving:0.9.0-devel bash -docker exec -it test bash +docker run -p 9292:9292 --name test_cpu -dit registry.baidubce.com/paddlepaddle/serving:0.9.0-devel bash +docker exec -it test_cpu bash git clone https://github.com/PaddlePaddle/Serving ``` + + + **GPU：** ``` # 启动 GPU Docker docker pull registry.baidubce.com/paddlepaddle/serving:0.9.0-cuda11.2-cudnn8-devel -nvidia-docker run -p 9292:9292 --name test -dit registry.baidubce.com/paddlepaddle/serving:0.9.0-cuda11.2-cudnn8-devel bash -nvidia-docker exec -it test bash +nvidia-docker run -p 9292:9292 --name test_gpu -dit registry.baidubce.com/paddlepaddle/serving:0.9.0-cuda11.2-cudnn8-devel bash +nvidia-docker exec -it test_gpu bash +git clone https://github.com/PaddlePaddle/Serving +``` + + + +**ARM & XPU: ** +``` +docker pull registry.baidubce.com/paddlepaddle/serving:xpu-arm +docker run -p 9292:9292 --name test_arm_xpu -dit registry.baidubce.com/paddlepaddle/serving:xpu-arm bash +docker exec -it test_arm_xpu bash git clone https://github.com/PaddlePaddle/Serving ``` ### 1.2 Paddle开发镜像（CPU/GPU 2选1） + + + **CPU：** ``` ### 启动 CPU Docker @@ -71,6 +96,9 @@ git clone https://github.com/PaddlePaddle/Serving ### Paddle开发镜像需要执行以下脚本增加Serving所需依赖项 bash Serving/tools/paddle_env_install.sh ``` + + + **GPU：** ``` ### 启动 GPU Docker @@ -103,6 +131,7 @@ pip3 install -r python/requirements.txt ### 2.1 在线安装 +在线安装采用 `pypi` 下载并安装的方式。 ```shell pip3 install paddle-serving-client==0.9.0 -i https://pypi.tuna.tsinghua.edu.cn/simple @@ -158,6 +187,7 @@ pip3 install https://paddle-inference-lib.bj.bcebos.com/2.3.0/python/Linux/GPU/x ### 2.2 离线安装 +离线安装是指所有的 Paddle 和 Serving 包和依赖库，传入到无网或弱网环境下安装。 **1.安装离线 Wheel 包** @@ -223,6 +253,24 @@ python3 install.py --cuda_version="" --python_version="py39" --device="cpu" --se python3 install.py --cuda_version="112" --python_version="py36" --device="GPU" --serving_version="no_install" --paddle_version="2.3.0" ``` + + +### 2.3 ARM & XPU 安装 wheel 包 + +由于使用 ARM 和 XPU 的用户较少，安装此环境的 Wheel 单独提供如下，其中 `paddle_serving_client` 仅提供 `py36` 的版本，如需其他版本请与我们联系。 + +``` +pip3.6 install https://paddle-serving.bj.bcebos.com/test-dev/whl/arm/paddle_serving_app-0.9.0-py3-none-any.whl +pip3.6 install https://paddle-serving.bj.bcebos.com/test-dev/whl/arm/paddle_serving_client-0.9.0-cp36-none-any.whl +pip3.6 install https://paddle-serving.bj.bcebos.com/test-dev/whl/arm/paddle_serving_server_xpu-0.9.0.post2-py3-none-any.whl +``` + +二进制包地址: +``` +wget https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-xpu-aarch64-0.9.0.tar.gz +``` + + ## 3.环境检查 diff --git a/doc/Install_EN.md b/doc/Install_EN.md index 9d6bbf0bf..b62213c14 100644 --- a/doc/Install_EN.md +++ b/doc/Install_EN.md @@ -4,10 +4,16 @@ - [1.Use devel docker](#1) - [Serving devel images](#1.1) + - [CPU images](#1.1.1) + - [GPU images](#1.1.2) + - [ARM & XPU images](#1.1.3) - [Paddle devel images](#1.2) + - [CPU images](#1.2.1) + - [GPU images](#1.2.2) - [2.Install Wheel Packages](#2) - [Online Install](#2.1) - [Offline Install](#2.2) + - [ARM & XPU Install](#2.3) - [3.Installation Check](#3) **Strongly recommend** you build **Paddle Serving** in Docker. For more images, please refer to [Docker Image List](Docker_Images_CN.md). @@ -28,6 +34,7 @@ | CUDA10.2 + cuDNN 7 | 0.9.0-cuda10.2-cudnn7-devel | Ubuntu 16 | 2.3.0-gpu-cuda10.2-cudnn7 | Ubuntu 18 | CUDA10.2 + cuDNN 8 | 0.9.0-cuda10.2-cudnn8-devel | Ubuntu 16 | None | None | | CUDA11.2 + cuDNN 8 | 0.9.0-cuda11.2-cudnn8-devel | Ubuntu 16 | 2.3.0-gpu-cuda11.2-cudnn8 | Ubuntu 18 | +| ARM + XPU | xpu-arm | CentOS 8.3 | None | None | For **Windows 10 users**, please refer to the document [Paddle Serving Guide for Windows Platform](Windows_Tutorial_CN.md). @@ -36,46 +43,68 @@ For **Windows 10 users**, please refer to the document [Paddle Serving Guide for ### 1.1 Serving Devel Images (CPU/GPU 2 choose 1) + + **CPU:** ``` # Start CPU Docker Container docker pull registry.baidubce.com/paddlepaddle/serving:0.9.0-devel -docker run -p 9292:9292 --name test -dit registry.baidubce.com/paddlepaddle/serving:0.9.0-devel bash -docker exec -it test bash +docker run -p 9292:9292 --name test_cpu -dit registry.baidubce.com/paddlepaddle/serving:0.9.0-devel bash +docker exec -it test_cpu bash git clone https://github.com/PaddlePaddle/Serving ``` + + + **GPU:** ``` # Start GPU Docker Container docker pull registry.baidubce.com/paddlepaddle/serving:0.9.0-cuda11.2-cudnn7-devel -nvidia-docker run -p 9292:9292 --name test -dit docker pull registry.baidubce.com/paddlepaddle/serving:0.9.0-cuda11.2-cudnn7-devel bash -nvidia-docker exec -it test bash +nvidia-docker run -p 9292:9292 --name test_gpu -dit docker pull registry.baidubce.com/paddlepaddle/serving:0.9.0-cuda11.2-cudnn7-devel bash +nvidia-docker exec -it test_gpu bash +git clone https://github.com/PaddlePaddle/Serving +``` + + + +**ARM & XPU: ** +``` +docker pull registry.baidubce.com/paddlepaddle/serving:xpu-arm +docker run -p 9292:9292 --name test_arm_xpu -dit registry.baidubce.com/paddlepaddle/serving:xpu-arm bash +docker exec -it test_arm_xpu bash git clone https://github.com/PaddlePaddle/Serving ``` ### 1.2 Paddle Devel Images (choose any codeblock of CPU/GPU) + + + **CPU:** -``` +```shell # Start CPU Docker Container docker pull registry.baidubce.com/paddlepaddle/paddle:2.3.0 -docker run -p 9292:9292 --name test -dit registry.baidubce.com/paddlepaddle/paddle:2.3.0 bash -docker exec -it test bash +docker run -p 9292:9292 --name test_cpu -dit registry.baidubce.com/paddlepaddle/paddle:2.3.0 bash +docker exec -it test_cpu bash git clone https://github.com/PaddlePaddle/Serving -# Paddle dev image needs to run the following script to increase the dependencies required by Serving +### Paddle dev image needs to run the following script to increase the dependencies required by Serving bash Serving/tools/paddle_env_install.sh ``` + + + **GPU:** -``` -# Start GPU Docker + +```shell +### Start GPU Docker nvidia-docker pull registry.baidubce.com/paddlepaddle/paddle:2.3.0-gpu-cuda11.2-cudnn8 -nvidia-docker run -p 9292:9292 --name test -dit registry.baidubce.com/paddlepaddle/paddle:2.3.0-gpu-cuda11.2-cudnn8 bash -nvidia-docker exec -it test bash +nvidia-docker run -p 9292:9292 --name test_gpu -dit registry.baidubce.com/paddlepaddle/paddle:2.3.0-gpu-cuda11.2-cudnn8 bash +nvidia-docker exec -it test_gpu bash git clone https://github.com/PaddlePaddle/Serving -# Paddle development image needs to execute the following script to increase the dependencies required by Serving +### Paddle development image needs to execute the following script to increase the dependencies required by Serving bash Serving/tools/paddle_env_install.sh ``` @@ -98,6 +127,7 @@ Install the service whl package. There are three types of client, app and server ### 2.1 Online Install +Online installation uses `pypi` to download and install. ```shell pip3 install paddle-serving-client==0.9.0 -i https://pypi.tuna.tsinghua.edu.cn/simple @@ -152,6 +182,7 @@ pip3 install https://paddle-inference-lib.bj.bcebos.com/2.3.0/python/Linux/GPU/x ### 2.2 Offline Install +Offline installation is to download all Paddle and Serving packages and dependent libraries, and install them in a no-network or weak-network environment. **1.Install offline wheel packages** @@ -210,6 +241,22 @@ python3 install.py --cuda_version="" --python_version="py39" --device="cpu" --se python3 install.py --cuda_version="112" --python_version="py36" --device="GPU" --serving_version="no_install" --paddle_version="2.3.0" ``` + + +### 2.3 ARM & XPU Install + +Since there are few users using ARM and XPU, the Wheel for installing this environment is provided separately as follows, among which `paddle_serving_client` only provides the `py36` version, if you need other versions, please contact us. +``` +pip3.6 install https://paddle-serving.bj.bcebos.com/test-dev/whl/arm/paddle_serving_app-0.9.0-py3-none-any.whl +pip3.6 install https://paddle-serving.bj.bcebos.com/test-dev/whl/arm/paddle_serving_client-0.9.0-cp36-none-any.whl +pip3.6 install https://paddle-serving.bj.bcebos.com/test-dev/whl/arm/paddle_serving_server_xpu-0.9.0.post2-py3-none-any.whl +``` + +Download binary package address: +``` +wget https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-xpu-aarch64-0.9.0.tar.gz +``` + ## 3.Installation Check diff --git a/doc/Latest_Packages_CN.md b/doc/Latest_Packages_CN.md index ee5a30313..4666b2ea1 100644 --- a/doc/Latest_Packages_CN.md +++ b/doc/Latest_Packages_CN.md @@ -48,22 +48,23 @@ ### Wheel包链接 适用ARM CPU环境的昆仑Wheel包： -``` + +```shell # paddle-serving-server -https://paddle-serving.bj.bcebos.com/whl/xpu/arm/paddle_serving_server_xpu-0.0.0.post2-py3-none-any.whl +wget https://paddle-serving.bj.bcebos.com/test-dev/whl/arm/paddle_serving_app-0.9.0-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 +wget https://paddle-serving.bj.bcebos.com/test-dev/whl/arm/paddle_serving_client-0.9.0-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 +wget https://paddle-serving.bj.bcebos.com/test-dev/whl/arm/paddle_serving_server_xpu-0.9.0.post2-py3-none-any.whl # SERVING BIN -https://paddle-serving.bj.bcebos.com/bin/serving-xpu-aarch64-0.0.0.tar.gz +wget https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-xpu-aarch64-0.9.0.tar.gz ``` -适用于x86 CPU环境的昆仑Wheel包： -``` +适用于ARM & XPU 的 v0.9.0 版本 Wheel包： +```shell https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_xpu-0.9.0.post2-py3-none-any.whl - ``` + diff --git a/doc/Latest_Packages_EN.md b/doc/Latest_Packages_EN.md index b0cb1397c..3cdcb3449 100644 --- a/doc/Latest_Packages_EN.md +++ b/doc/Latest_Packages_EN.md @@ -46,23 +46,22 @@ for kunlun user who uses arm-xpu or x86-xpu can download the wheel packages as f ### Wheel Package Links -for arm kunlun user -``` +for arm kunlun user, +```shell # paddle-serving-server -https://paddle-serving.bj.bcebos.com/whl/xpu/arm/paddle_serving_server_xpu-0.0.0.post2-py3-none-any.whl +wget https://paddle-serving.bj.bcebos.com/test-dev/whl/arm/paddle_serving_app-0.9.0-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 +wget https://paddle-serving.bj.bcebos.com/test-dev/whl/arm/paddle_serving_client-0.9.0-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 +wget https://paddle-serving.bj.bcebos.com/test-dev/whl/arm/paddle_serving_server_xpu-0.9.0.post2-py3-none-any.whl # SERVING BIN -https://paddle-serving.bj.bcebos.com/bin/serving-xpu-aarch64-0.0.0.tar.gz +wget https://paddle-serving.bj.bcebos.com/test-dev/bin/serving-xpu-aarch64-0.9.0.tar.gz ``` -for x86 kunlun user -``` +for x86 xpu user, the wheel packages are here. +```shell https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_xpu-0.9.0.post2-py3-none-any.whl - ```