andsonder/tensorrt

NVIDIA® TensorRT™, an SDK for high-performance deep learning inference, includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for inference applications.

TensorRT Open Source Software

This repository contains the Open Source Software (OSS) components of NVIDIA TensorRT. It includes the sources for TensorRT plugins and parsers (Caffe and ONNX), as well as sample applications demonstrating usage and capabilities of the TensorRT platform. These open source software components are a subset of the TensorRT General Availability (GA) release with some extensions and bug-fixes.

• For code contributions to TensorRT-OSS, please see our Contribution Guide and Coding Guidelines.
• For a summary of new additions and updates shipped with TensorRT-OSS releases, please refer to the Changelog.
• For business inquiries, please contact [email protected]
• For press and other inquiries, please contact Hector Marinez at [email protected]

Need enterprise support? NVIDIA global support is available for TensorRT with the NVIDIA AI Enterprise software suite. Check out NVIDIA LaunchPad for free access to a set of hands-on labs with TensorRT hosted on NVIDIA infrastructure.

Join the TensorRT and Triton community and stay current on the latest product updates, bug fixes, content, best practices, and more.

Prebuilt TensorRT Python Package

We provide the TensorRT Python package for an easy installation.
To install:

pip install tensorrt

You can skip the Build section to enjoy TensorRT with Python.

Build

Prerequisites

To build the TensorRT-OSS components, you will first need the following software packages.

TensorRT GA build

• TensorRT v8.5.3.1

System Packages

• CUDA
  • Recommended versions:
  • cuda-11.8.0 + cuDNN-8.6
  • cuda-10.2 + cuDNN-8.4
• GNU make >= v4.1
• cmake >= v3.13
• python >= v3.6.9, <= v3.10.x
• pip >= v19.0
• Essential utilities
  • git, pkg-config, wget

Optional Packages

• Containerized build

  • Docker >= 19.03
  • NVIDIA Container Toolkit

• Toolchains and SDKs

  • (Cross compilation for Jetson platform) NVIDIA JetPack >= 5.0 (current support only for TensorRT 8.4.0)
  • (Cross compilation for QNX platform) QNX Toolchain

• PyPI packages (for demo applications/tests)

  • onnx 1.9.0
  • onnxruntime 1.8.0
  • tensorflow-gpu >= 2.5.1
  • Pillow >= 9.0.1
  • pycuda < 2021.1
  • numpy
  • pytest

• Code formatting tools (for contributors)

  • Clang-format
  • Git-clang-format

  NOTE: onnx-tensorrt, cub, and protobuf packages are downloaded along with TensorRT OSS, and not required to be installed.

Downloading TensorRT Build

1. Download TensorRT OSS

   git clone -b master https://github.com/nvidia/TensorRT TensorRT
   cd TensorRT
   git submodule update --init --recursive

2. (Optional - if not using TensorRT container) Specify the TensorRT GA release build path

   If using the TensorRT OSS build container, TensorRT libraries are preinstalled under /usr/lib/x86_64-linux-gnu and you may skip this step.

   Else download and extract the TensorRT GA build from NVIDIA Developer Zone.

   Example: Ubuntu 20.04 on x86-64 with cuda-11.8.0

   cd ~/Downloads
   tar -xvzf TensorRT-8.5.3.1.Linux.x86_64-gnu.cuda-11.8.cudnn8.6.tar.gz
   export TRT_LIBPATH=`pwd`/TensorRT-8.5.3.1

3. (Optional - for Jetson builds only) Download the JetPack SDK

   1. Download and launch the JetPack SDK manager. Login with your NVIDIA developer account.
   2. Select the platform and target OS (example: Jetson AGX Xavier, Linux Jetpack 5.0), and click Continue.
   3. Under Download & Install Options change the download folder and select Download now, Install later. Agree to the license terms and click Continue.
   4. Move the extracted files into the <TensorRT-OSS>/docker/jetpack_files folder.

Setting Up The Build Environment

For Linux platforms, we recommend that you generate a docker container for building TensorRT OSS as described below. For native builds, please install the prerequisite System Packages.

1. Generate the TensorRT-OSS build container.

   The TensorRT-OSS build container can be generated using the supplied Dockerfiles and build scripts. The build containers are configured for building TensorRT OSS out-of-the-box.

   Example: Ubuntu 20.04 on x86-64 with cuda-11.8.0 (default)

   ./docker/build.sh --file docker/ubuntu-20.04.Dockerfile --tag tensorrt-ubuntu20.04-cuda11.8

   Example: CentOS/RedHat 7 on x86-64 with cuda-10.2

   ./docker/build.sh --file docker/centos-7.Dockerfile --tag tensorrt-centos7-cuda10.2 --cuda 10.2

   Example: Ubuntu 20.04 cross-compile for Jetson (aarch64) with cuda-11.4.2 (JetPack SDK)

   ./docker/build.sh --file docker/ubuntu-cross-aarch64.Dockerfile --tag tensorrt-jetpack-cuda11.4

   Example: Ubuntu 20.04 on aarch64 with cuda-11.4.2

   ./docker/build.sh --file docker/ubuntu-20.04-aarch64.Dockerfile --tag tensorrt-aarch64-ubuntu20.04-cuda11.4

2. Launch the TensorRT-OSS build container.

   Example: Ubuntu 20.04 build container

   ./docker/launch.sh --tag tensorrt-ubuntu20.04-cuda11.8 --gpus all

   NOTE:
   1. Use the --tag corresponding to build container generated in Step 1.
   2. NVIDIA Container Toolkit is required for GPU access (running TensorRT applications) inside the build container.
   3. sudo password for Ubuntu build containers is 'nvidia'.
   4. Specify port number using --jupyter <port> for launching Jupyter notebooks.

Building TensorRT-OSS

• Generate Makefiles and build.

  Example: Linux (x86-64) build with default cuda-11.8.0

   cd $TRT_OSSPATH
   mkdir -p build && cd build
   cmake .. -DTRT_LIB_DIR=$TRT_LIBPATH -DTRT_OUT_DIR=`pwd`/out
   make -j$(nproc)

  NOTE: On CentOS7, the default g++ version does not support C++14. For native builds (not using the CentOS7 build container), first install devtoolset-8 to obtain the updated g++ toolchain as follows:

  yum -y install centos-release-scl
  yum-config-manager --enable rhel-server-rhscl-7-rpms
  yum -y install devtoolset-8
  export PATH="/opt/rh/devtoolset-8/root/bin:${PATH}

  Example: Linux (aarch64) build with default cuda-11.8.0

   cd $TRT_OSSPATH
   mkdir -p build && cd build
   cmake .. -DTRT_LIB_DIR=$TRT_LIBPATH -DTRT_OUT_DIR=`pwd`/out -DCMAKE_TOOLCHAIN_FILE=$TRT_OSSPATH/cmake/toolchains/cmake_aarch64-native.toolchain
   make -j$(nproc)

  Example: Native build on Jetson (aarch64) with cuda-11.4

  cd $TRT_OSSPATH
  mkdir -p build && cd build
  cmake .. -DTRT_LIB_DIR=$TRT_LIBPATH -DTRT_OUT_DIR=`pwd`/out -DTRT_PLATFORM_ID=aarch64 -DCUDA_VERSION=11.4
  CC=/usr/bin/gcc make -j$(nproc)

  NOTE: C compiler must be explicitly specified via CC= for native aarch64 builds of protobuf.

  Example: Ubuntu 20.04 Cross-Compile for Jetson (aarch64) with cuda-11.4 (JetPack)

  cd $TRT_OSSPATH
  mkdir -p build && cd build
  cmake .. -DCMAKE_TOOLCHAIN_FILE=$TRT_OSSPATH/cmake/toolchains/cmake_aarch64.toolchain -DCUDA_VERSION=11.4 -DCUDNN_LIB=/pdk_files/cudnn/usr/lib/aarch64-linux-gnu/libcudnn.so -DCUBLAS_LIB=/usr/local/cuda-11.4/targets/aarch64-linux/lib/stubs/libcublas.so -DCUBLASLT_LIB=/usr/local/cuda-11.4/targets/aarch64-linux/lib/stubs/libcublasLt.so -DTRT_LIB_DIR=/pdk_files/tensorrt/lib
  
  make -j$(nproc)

  NOTE: The latest JetPack SDK v5.0 only supports TensorRT 8.4.0.

  NOTE:
  1. The default CUDA version used by CMake is 11.8.0. To override this, for example to 10.2, append -DCUDA_VERSION=10.2 to the cmake command.
  2. If samples fail to link on CentOS7, create this symbolic link: ln -s $TRT_OUT_DIR/libnvinfer_plugin.so $TRT_OUT_DIR/libnvinfer_plugin.so.8

• Required CMake build arguments are:

  • TRT_LIB_DIR: Path to the TensorRT installation directory containing libraries.
  • TRT_OUT_DIR: Output directory where generated build artifacts will be copied.

• Optional CMake build arguments:

  • CMAKE_BUILD_TYPE: Specify if binaries generated are for release or debug (contain debug symbols). Values consists of [Release] | Debug
  • CUDA_VERISON: The version of CUDA to target, for example [11.7.1].
  • CUDNN_VERSION: The version of cuDNN to target, for example [8.6].
  • PROTOBUF_VERSION: The version of Protobuf to use, for example [3.0.0]. Note: Changing this will not configure CMake to use a system version of Protobuf, it will configure CMake to download and try building that version.
  • CMAKE_TOOLCHAIN_FILE: The path to a toolchain file for cross compilation.
  • BUILD_PARSERS: Specify if the parsers should be built, for example [ON] | OFF. If turned OFF, CMake will try to find precompiled versions of the parser libraries to use in compiling samples. First in ${TRT_LIB_DIR}, then on the system. If the build type is Debug, then it will prefer debug builds of the libraries before release versions if available.
  • BUILD_PLUGINS: Specify if the plugins should be built, for example [ON] | OFF. If turned OFF, CMake will try to find a precompiled version of the plugin library to use in compiling samples. First in ${TRT_LIB_DIR}, then on the system. If the build type is Debug, then it will prefer debug builds of the libraries before release versions if available.
  • BUILD_SAMPLES: Specify if the samples should be built, for example [ON] | OFF.
  • GPU_ARCHS: GPU (SM) architectures to target. By default we generate CUDA code for all major SMs. Specific SM versions can be specified here as a quoted space-separated list to reduce compilation time and binary size. Table of compute capabilities of NVIDIA GPUs can be found here. Examples:
    • NVidia A100: -DGPU_ARCHS="80"
    • Tesla T4, GeForce RTX 2080: -DGPU_ARCHS="75"
    • Titan V, Tesla V100: -DGPU_ARCHS="70"
    • Multiple SMs: -DGPU_ARCHS="80 75"
  • TRT_PLATFORM_ID: Bare-metal build (unlike containerized cross-compilation) on non Linux/x86 platforms must explicitly specify the target platform. Currently supported options: x86_64 (default), aarch64

References

TensorRT Resources

• TensorRT Developer Home
• TensorRT QuickStart Guide
• TensorRT Developer Guide
• TensorRT Sample Support Guide
• TensorRT ONNX Tools
• TensorRT Discussion Forums
• TensorRT Release Notes

Known Issues

• Please refer to TensorRT 8.5 Release Notes