Precompiled Binaries

Torch-TensorRT 2.x is centered primarily around Python. As such, precompiled releases can be found on


You need to have CUDA, PyTorch, and TensorRT (python package is sufficient) installed to use Torch-TensorRT

Installing Torch-TensorRT

You can install the python package using

python -m pip install torch torch-tensorrt tensorrt

Installing Torch-TensorRT for a specific CUDA version

Similar to PyTorch, Torch-TensorRT has builds compiled for different versions of CUDA. These are distributed on PyTorch’s package index

For example CUDA 11.8

python -m pip install torch torch-tensorrt tensorrt --extra-index-url

Installing Nightly Builds

Torch-TensorRT distributed nightlies targeting the PyTorch nightly. These can be installed from the PyTorch nightly package index (separated by CUDA version)

python -m pip install --pre torch torch-tensorrt tensorrt --extra-index-url

C++ Precompiled Binaries (TorchScript Only)

Precompiled tarballs for releases are provided here:

Compiling From Source

Dependencies for Compilation

  • Torch-TensorRT is built with Bazel, so begin by installing it.

    export BAZEL_VERSION=$(cat <PATH_TO_TORCHTRT_ROOT>/.bazelversion)
    mkdir bazel
    cd bazel
    curl -fSsL -O$BAZEL_VERSION/bazel-$
    unzip bazel-$
    bash ./
    cp output/bazel /usr/local/bin/
  • You will also need to have CUDA installed on the system (or if running in a container, the system must have the CUDA driver installed and the container must have CUDA)

  • The correct LibTorch and TensorRT versions will be pulled down for you by bazel.

    NOTE: By default bazel will pull the latest nightly from For building main, this is usually sufficient however if there is a specific PyTorch you are targeting, edit these locations with updated URLs/paths:

  • TensorRT is not required to be installed on the system to build Torch-TensorRT, in fact this is preferable to ensure reproducable builds. If versions other than the default are needed point the WORKSPACE file to the URL of the tarball or download the tarball for TensorRT from and update the paths in the WORKSPACE file here

    For example:

        name = "tensorrt",
        build_file = "@//third_party/tensorrt/archive:BUILD",
        sha256 = "<TENSORRT SHA256>", # Optional but recommended
        strip_prefix = "TensorRT-<TENSORRT VERSION>",
        urls = [
            # OR
            "file:///<ABSOLUTE PATH TO FILE>/TensorRT-<TENSORRT VERSION>.Linux.x86_64-gnu.cuda-<CUDA VERSION>.tar.gz"

    Remember at runtime, these libraries must be added to your LD_LIBRARY_PATH explicity

If you have a local version of TensorRT installed, this can be used as well by commenting out the above lines and uncommenting the following lines

Building the Package

Once the WORKSPACE has been configured properly, all that is required to build torch-tensorrt is the following command

python -m pip install --pre . --extra-index-url

To build the wheel file

python -m pip wheel --no-deps --pre . --extra-index-url -w dist

Building the C++ Library (TorchScript Only)

Release Build

bazel build //:libtorchtrt -c opt

A tarball with the include files and library can then be found in bazel-bin

Debug Build

To build with debug symbols use the following command

bazel build //:libtorchtrt -c dbg

A tarball with the include files and library can then be found in bazel-bin

Pre CXX11 ABI Build

To build using the pre-CXX11 ABI use the pre_cxx11_abi config

bazel build //:libtorchtrt --config pre_cxx11_abi -c [dbg/opt]

A tarball with the include files and library can then be found in bazel-bin

Choosing the Right ABI

Likely the most complicated thing about compiling Torch-TensorRT is selecting the correct ABI. There are two options which are incompatible with each other, pre-cxx11-abi and the cxx11-abi. The complexity comes from the fact that while the most popular distribution of PyTorch (wheels downloaded from directly) use the pre-cxx11-abi, most other distributions you might encounter (e.g. ones from NVIDIA - NGC containers, and builds for Jetson as well as certain libtorch builds and likely if you build PyTorch from source) use the cxx11-abi. It is important you compile Torch-TensorRT using the correct ABI to function properly. Below is a table with general pairings of PyTorch distribution sources and the recommended commands:

PyTorch Source

Recommended Python Compilation Command

Recommended C++ Compilation Command

PyTorch whl file from

python -m pip install .

bazel build //:libtorchtrt -c opt –config pre_cxx11_abi

libtorch-shared-with-deps-*.zip from

python -m pip install .

bazel build //:libtorchtrt -c opt –config pre_cxx11_abi

libtorch-cxx11-abi-shared-with-deps-*.zip from

python bdist_wheel –use-cxx11-abi

bazel build //:libtorchtrt -c opt

PyTorch preinstalled in an NGC container

python bdist_wheel –use-cxx11-abi

bazel build //:libtorchtrt -c opt

PyTorch from the NVIDIA Forums for Jetson

python bdist_wheel –use-cxx11-abi

bazel build //:libtorchtrt -c opt

PyTorch built from Source

python bdist_wheel –use-cxx11-abi

bazel build //:libtorchtrt -c opt

NOTE: For all of the above cases you must correctly declare the source of PyTorch you intend to use in your WORKSPACE file for both Python and C++ builds. See below for more information

Building with CMake (TorchScript Only)

It is possible to build the API libraries (in cpp/) and the torchtrtc executable using CMake instead of Bazel. Currently, the python API and the tests cannot be built with CMake. Begin by installing CMake.

  • Latest releases of CMake and instructions on how to install are available for different platforms [on their website](

A few useful CMake options include:

  • CMake finders for TensorRT are provided in cmake/Modules. In order for CMake to use them, pass -DCMAKE_MODULE_PATH=cmake/Modules when configuring the project with CMake.

  • Libtorch provides its own CMake finder. In case CMake doesn’t find it, pass the path to your install of libtorch with -DTorch_DIR=<path to libtorch>/share/cmake/Torch

  • If TensorRT is not found with the provided cmake finder, specify -DTensorRT_ROOT=<path to TensorRT>

  • Finally, configure and build the project in a build directory of your choice with the following command from the root of Torch-TensorRT project:

cmake -S. -B<build directory> \
    [-DCMAKE_MODULE_PATH=cmake/Module] \
    [-DTorch_DIR=<path to libtorch>/share/cmake/Torch] \
    [-DTensorRT_ROOT=<path to TensorRT>] \
cmake --build <build directory>

Building Natively on aarch64 (Jetson)


Install or compile a build of PyTorch/LibTorch for aarch64

NVIDIA hosts builds the latest release branch for Jetson here:

Enviorment Setup

To build natively on aarch64-linux-gnu platform, configure the WORKSPACE with local available dependencies.

  1. Replace WORKSPACE with the corresponding WORKSPACE file in //toolchains/jp_workspaces

  2. Configure the correct paths to directory roots containing local dependencies in the new_local_repository rules:

    NOTE: If you installed PyTorch using a pip package, the correct path is the path to the root of the python torch package. In the case that you installed with sudo pip install this will be /usr/local/lib/python3.8/dist-packages/torch. In the case you installed with pip install --user this will be $HOME/.local/lib/python3.8/site-packages/torch.

In the case you are using NVIDIA compiled pip packages, set the path for both libtorch sources to the same path. This is because unlike PyTorch on x86_64, NVIDIA aarch64 PyTorch uses the CXX11-ABI. If you compiled for source using the pre_cxx11_abi and only would like to use that library, set the paths to the same path but when you compile make sure to add the flag --config=pre_cxx11_abi

    name = "libtorch",
    path = "/usr/local/lib/python3.8/dist-packages/torch",
    build_file = "third_party/libtorch/BUILD"

    name = "libtorch_pre_cxx11_abi",
    path = "/usr/local/lib/python3.8/dist-packages/torch",
    build_file = "third_party/libtorch/BUILD"

Compile C++ Library and Compiler CLI

NOTE: Due to shifting dependency locations between Jetpack 4.5 and 4.6 there is a now a flag to inform bazel of the Jetpack version

--platforms //toolchains:jetpack_x.x

Compile Torch-TensorRT library using bazel command:

bazel build //:libtorchtrt --platforms //toolchains:jetpack_5.0

Compile Python API

NOTE: Due to shifting dependencies locations between Jetpack 4.5 and newer Jetpack verisons there is now a flag for which sets the jetpack version (default: 5.0)

Compile the Python API using the following command from the //py directory:

python3 install --use-cxx11-abi

If you have a build of PyTorch that uses Pre-CXX11 ABI drop the --use-cxx11-abi flag

If you are building for Jetpack 4.5 add the --jetpack-version 5.0 flag


Access comprehensive developer documentation for PyTorch

View Docs


Get in-depth tutorials for beginners and advanced developers

View Tutorials


Find development resources and get your questions answered

View Resources