Install and Compile C++ Inference Library on Linux¶

Direct Download and Installation¶

Build from Source Code¶

Users can also compile C++ inference libraries from the PaddlePaddle core code by specifying the following compile options at compile time:

It is recommended to configure options according to the recommended values to avoid linking unnecessary libraries. Other options can be set if it is necessary.

Firstly we pull the latest code from github and install nccl.

git clone https://github.com/paddlepaddle/paddle
# Use git checkout to switch to stable versions such as v1.6.2
git checkout v1.6.2

git clone https://github.com/NVIDIA/nccl.git
make -j4
make install

note: nccl is not used but still needed in building. This dependence will be removed later.

build inference libs on server

Following codes set the configurations and execute building(PADDLE_ROOT should be set to the actual installing path of inference libs).

PADDLE_ROOT=/path/of/capi
git clone https://github.com/PaddlePaddle/Paddle.git
cd Paddle
mkdir build
cd build
cmake -DFLUID_INFERENCE_INSTALL_DIR=$PADDLE_ROOT \
      -DCMAKE_BUILD_TYPE=Release \
      -DWITH_PYTHON=OFF \
      -DWITH_MKL=OFF \
      -DWITH_GPU=OFF  \
      -DON_INFER=ON \
      ..
 make
 make inference_lib_dist

build inference libs on NVIDIA Jetson platforms

NVIDIA Jetson is an AI computing platform in embedded systems introduced by NVIDIA. Paddle Inference supports building inference libs on NVIDIA Jetson platforms. The steps are as following.

1. Prepare environments

Turn on hardware performance mode

sudo nvpmodel -m 0 && sudo jetson_clocks

if building on Nano hardwares, increase swap memory

# Increase DDR valid space. Default memory allocated is 16G, which is enough for Xavier. Following steps are for Nano hardwares.
sudo fallocate -l 5G /var/swapfile
sudo chmod 600 /var/swapfile
sudo mkswap /var/swapfile
sudo swapon /var/swapfile
sudo bash -c 'echo "/var/swapfile swap swap defaults 0 0" >> /etc/fstab'

2. Build paddle inference libs

cd Paddle
mkdir build
cd build
cmake .. \
  -DWITH_CONTRIB=OFF \
  -DWITH_MKL=OFF  \
  -DWITH_MKLDNN=OFF \
  -DWITH_TESTING=OFF \
  -DCMAKE_BUILD_TYPE=Release \
  -DON_INFER=ON \
  -DWITH_PYTHON=OFF \
  -DWITH_XBYAK=OFF  \
  -DWITH_NV_JETSON=ON
make -j4
# Generate inference libs
make inference_lib_dist -j4

3. Test with samples

System Message: WARNING/2 (/home/work/paddledoc/FluidDoc/doc/fluid/advanced_guide/inference_deployment/inference/build_and_install_lib_en.rst, line 122)

Enumerated list ends without a blank line; unexpected unindent.

Please refer to samples on https://www.paddlepaddle.org.cn/documentation/docs/zh/advanced_guide/performance_improving/inference_improving/paddle_tensorrt_infer.html#id2

FAQ

1. Error:

ERROR: ../aarch64-linux-gpn/crtn.o: Too many open files.

Fix this by increasing the number of files the system can open at the same time to 2048.

ulimit -n 2048

2. The building process hangs.

System Message: WARNING/2 (/home/work/paddledoc/FluidDoc/doc/fluid/advanced_guide/inference_deployment/inference/build_and_install_lib_en.rst, line 139)

Enumerated list ends without a blank line; unexpected unindent.

Might be downloading third-party libs. Wait or kill the building process and start again.

3. Lacking virtual destructors for IPluginFactory or IGpuAllocator when using TensorRT.

System Message: WARNING/2 (/home/work/paddledoc/FluidDoc/doc/fluid/advanced_guide/inference_deployment/inference/build_and_install_lib_en.rst, line 142)

Enumerated list ends without a blank line; unexpected unindent.

After downloading and installing TensorRT, add virtual destructors for IPluginFactory and IGpuAllocator in NvInfer.h:

virtual ~IPluginFactory() {};
virtual ~IGpuAllocator() {};

After successful compilation, dependencies required by the C++ inference library Will be stored in the PADDLE_ROOT directory. (dependencies including: (1) compiled PaddlePaddle inference library and header files; (2) third-party link libraries and header files; (3) version information and compilation option information)

The directory structure is:

PaddleRoot/
├── CMakeCache.txt
├── paddle
│   ├── include
│   │   ├── paddle_anakin_config.h
│   │   ├── paddle_analysis_config.h
│   │   ├── paddle_api.h
│   │   ├── paddle_inference_api.h
│   │   ├── paddle_mkldnn_quantizer_config.h
│   │   └── paddle_pass_builder.h
│   └── lib
│       ├── libpaddle_fluid.a
│       └── libpaddle_fluid.so
├── third_party
│   ├── boost
│   │   └── boost
│   ├── eigen3
│   │   ├── Eigen
│   │   └── unsupported
│   └── install
│       ├── gflags
│       ├── glog
│       ├── mkldnn
│       ├── mklml
│       ├── protobuf
│       ├── snappy
│       ├── snappystream
│       ├── xxhash
│       └── zlib
└── version.txt

The version information of the inference library is recorded in version.txt, including Git Commit ID, version of OpenBlas, MKL math library, or CUDA/CUDNN. For example:

GIT COMMIT ID: cc9028b90ef50a825a722c55e5fda4b7cd26b0d6
WITH_MKL: ON
WITH_MKLDNN: ON
WITH_GPU: ON
CUDA version: 8.0
CUDNN version: v7