It is recommended to use Docker to prepare the compilation environment for the Paddle service: [CPU Dockerfile.devel](../tools/Dockerfile.devel), [GPU Dockerfile.gpu.devel](../tools/Dockerfile.gpu.devel)
## 获取代码
## Get Code
``` python
gitclonehttps://github.com/PaddlePaddle/Serving
cdServing&&gitsubmoduleupdate--init--recursive
```
## PYTHONROOT设置
## PYTHONROOT Setting
```shell
# 例如python的路径为/usr/bin/python，可以设置PYTHONROOT
# for example, the path of python is /usr/bin/python, you can set /usr as PYTHONROOT
export PYTHONROOT=/usr/
```
## 编译Server部分
## Compile Server
### 集成CPU版本Paddle Inference Library
### Integrated CPU version paddle inference library
you can execute `make install` to put targets under directory `./output`, you need to add`-DCMAKE_INSTALL_PREFIX=./output`to specify output path to cmake command shown above.
### 集成GPU版本Paddle Inference Library
### Integrated GPU version paddle inference library
When running the python server, it will check the `SERVING_BIN` environment variable. If you want to use your own compiled binary file, set the environment variable to the path of the corresponding binary file, usually`export SERVING_BIN=${BUILD_DIR}/core/general-server/serving`.
Paddle Serving supports prediction on the GPU through the PaddlePaddle inference library. The WITH_GPU option is used to detect basic libraries such as CUDA/CUDNN on the system. If an appropriate version is detected, the GPU Kernel will be compiled when PaddlePaddle is compiled.
在裸机上编译Paddle Serving GPU版本，需要安装这些基础库：
To compile the Paddle Serving GPU version on bare metal, you need to install these basic libraries:
- CUDA
- CuDNN
- NCCL2
这里要注意的是：
Note here:
1. The basic library versions such as CUDA/CUDNN installed on the system where Serving is compiled, needs to be compatible with the actual GPU device. For example, the Tesla V100 card requires at least CUDA 9.0. If the version of the basic library such as CUDA used during compilation is too low, the generated GPU code is not compatible with the actual hardware device, which will cause the Serving process to fail to start or serious problems such as coredump.
2. Install the CUDA driver compatible with the actual GPU device on the system running Paddle Serving, and install the basic library compatible with the CUDA/CuDNN version used during compilation. If the version of CUDA/CuDNN installed on the system running Paddle Serving is lower than the version used at compile time, it may cause some cuda function call failures and other problems.
Download the corresponding CUDNN version from NVIDIA developer official website and decompressing it, add `-DCUDNN_ROOT` to cmake command, to specify the path of CUDNN.
### 如何让Paddle Serving编译系统探测到nccl库
### How to make the compiler detect the nccl library
After downloading the corresponding version of the nccl2 library from the NVIDIA developer official website and decompressing it, add the following environment variables (take nccl2.1.4 as an example):
