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.
.. code-block:: bash
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
It is recommended to configure options according to the recommended values to avoid the link to unnecessary library. Other options can be set if it is necessary.
**note**: nccl is not used but still needed in building. This dependence will be removed later.
**build inference libs on server**
The following code snippet pulls the latest code from github and specifies the compiling options (you need to replace PADDLE_ROOT with the installation path of the PaddlePaddle inference library):
Following codes set the configurations and execute building(PADDLE_ROOT should be set to the actual installing path of inference libs).
.. code-block:: bash
...
...
@@ -55,6 +77,79 @@ The following code snippet pulls the latest code from github and specifies the c
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
.. code-block:: bash
sudo nvpmodel -m 0 && sudo jetson_clocks
if building on Nano hardwares, increase swap memory
.. code-block:: bash
# Increase DDR valid space. Default memory allocated is 16G, which is enough for Xavier. Following steps are for Nano hardwares.
Please refer to samples on https://www.paddlepaddle.org.cn/documentation/docs/zh/advanced_usage/deploy/inference/paddle_tensorrt_infer.html#id2
**FAQ**
1. Error:
.. code-block:: bash
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.
.. code-block:: bash
ulimit -n 2048
2. The building process hangs.
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.
After downloading and installing TensorRT, add virtual destructors for IPluginFactory and IGpuAllocator in NvInfer.h:
.. code-block:: bash
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)
