ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
NVIDIA
NVIDIA
NVIDIA L4T TensorRT
Container
NVIDIA
NVIDIA
NVIDIA L4T TensorRT

NVIDIA TensorRT is a C++ library that facilitates high-performance inference on NVIDIA graphics processing units (GPUs). TensorRT takes a trained network and produces a highly optimized runtime engine that performs inference for that network.

LayerLabelCreated
sha256:1e5b7f92c48ee15d31e8b7d2646caa5c12c7cd5dd773c2d832197065757f376cCOPY
NGC-DL-CONTAINER-LICENSE /
08/25/2022 8:36 PM UTC
sha256:e8d5bbb2e1f5da56efb8a131ca3e79bd7ed1b7cf6940549a2f5eb32dfa9e4467RUN
CUDA_VERSION=11.4.14 CUDA_VERSION_MAJOR_MINOR=11.4 CUDA_KITPICK_RC_VERSION=011 TRT_VERSION_MAJOR_MINOR_HYPHEN=8-4 TRT_VERSION=8.4.1 TRT_VERSION_FULL=8.4.1.5 TRT_LIBNVINFER_VERSION=8.4.1 TRT_KITPICK_RC_VERSION=003 NVIDIA_TENSORRT_VERSION=8.4.1 PYVER=3.8 pip install --no-cache-dir --extra-index-url https://pypi.ngc.nvidia.com --extra-index-url https://tensorrt-read-only:Tensorrt\@123@urm.nvidia.com/artifactory/api/pypi/sw-tensorrt-pypi/simple polygraphy
08/25/2022 8:36 PM UTC
sha256:45380c1f729e9b231cd81ea4b2e9da64e96f088af2151f92e74810c5dbecc28eRUN
CUDA_VERSION=11.4.14 CUDA_VERSION_MAJOR_MINOR=11.4 CUDA_KITPICK_RC_VERSION=011 TRT_VERSION_MAJOR_MINOR_HYPHEN=8-4 TRT_VERSION=8.4.1 TRT_VERSION_FULL=8.4.1.5 TRT_LIBNVINFER_VERSION=8.4.1 TRT_KITPICK_RC_VERSION=003 NVIDIA_TENSORRT_VERSION=8.4.1 PYVER=3.8 export PY=$(python -c 'import sys; print(str(sys.version_info[0])+str(sys.version_info[1]))') &&
  pip install /builds/TensorRT-${TRT_VERSION_FULL}/graphsurgeon/graphsurgeon-0.4.6-py2.py3-none-any.whl /builds/TensorRT-${TRT_VERSION_FULL}/python/tensorrt-${TRT_VERSION_FULL}-cp${PY}-none-linux_aarch64.whl /builds/TensorRT-${TRT_VERSION_FULL}/uff/uff-0.6.9-py2.py3-none-any.whl /builds/TensorRT-${TRT_VERSION_FULL}/onnx_graphsurgeon/onnx_graphsurgeon-0.3.12-py2.py3-none-any.whl
08/25/2022 8:36 PM UTC
sha256:ef67020da1a3d3f3d819d0c0862ff4f4f4063e01133da2aec5c088c91324f830RUN
CUDA_VERSION=11.4.14 CUDA_VERSION_MAJOR_MINOR=11.4 CUDA_KITPICK_RC_VERSION=011 TRT_VERSION_MAJOR_MINOR_HYPHEN=8-4 TRT_VERSION=8.4.1 TRT_VERSION_FULL=8.4.1.5 TRT_LIBNVINFER_VERSION=8.4.1 TRT_KITPICK_RC_VERSION=003 NVIDIA_TENSORRT_VERSION=8.4.1 PYVER=3.8 apt update &&
  apt install -f -y protobuf-compiler libprotobuf-dev
08/25/2022 8:35 PM UTC
sha256:0b1315fbce99f5f3b63063d2a04ee43732a326936820305c1439795aab339159RUN
CUDA_VERSION=11.4.14 CUDA_VERSION_MAJOR_MINOR=11.4 CUDA_KITPICK_RC_VERSION=011 TRT_VERSION_MAJOR_MINOR_HYPHEN=8-4 TRT_VERSION=8.4.1 TRT_VERSION_FULL=8.4.1.5 TRT_LIBNVINFER_VERSION=8.4.1 TRT_KITPICK_RC_VERSION=003 NVIDIA_TENSORRT_VERSION=8.4.1 PYVER=3.8 pip install --upgrade --no-cache-dir numpy &&
  pip install --upgrade --no-cache-dir pycuda pillow
08/25/2022 8:35 PM UTC
sha256:7c7722dfb78177d5272e8b6ab07334192788a2e361b52e574da6f19961a664b9RUN
CUDA_VERSION=11.4.14 CUDA_VERSION_MAJOR_MINOR=11.4 CUDA_KITPICK_RC_VERSION=011 TRT_VERSION_MAJOR_MINOR_HYPHEN=8-4 TRT_VERSION=8.4.1 TRT_VERSION_FULL=8.4.1.5 TRT_LIBNVINFER_VERSION=8.4.1 TRT_KITPICK_RC_VERSION=003 NVIDIA_TENSORRT_VERSION=8.4.1 PYVER=3.8 curl -O https://bootstrap.pypa.io/get-pip.py &&
  python get-pip.py &&
  rm get-pip.py
08/25/2022 8:22 PM UTC
sha256:d862272b01109140d8f0c4802ca6d980fefc527c0a92df20686e2f5ba3111442RUN
CUDA_VERSION=11.4.14 CUDA_VERSION_MAJOR_MINOR=11.4 CUDA_KITPICK_RC_VERSION=011 TRT_VERSION_MAJOR_MINOR_HYPHEN=8-4 TRT_VERSION=8.4.1 TRT_VERSION_FULL=8.4.1.5 TRT_LIBNVINFER_VERSION=8.4.1 TRT_KITPICK_RC_VERSION=003 NVIDIA_TENSORRT_VERSION=8.4.1 PYVER=3.8 MAJ=`echo "$PYVER" | cut -c1-1` &&
  rm -f /usr/bin/python$MAJ &&
  ln -s /usr/bin/python$PYVER /usr/bin/python$MAJ
08/25/2022 8:22 PM UTC
sha256:4968a8528c2894707b09e54cc59112fd187c7b1a9327772565ab716a10dee377RUN
CUDA_VERSION=11.4.14 CUDA_VERSION_MAJOR_MINOR=11.4 CUDA_KITPICK_RC_VERSION=011 TRT_VERSION_MAJOR_MINOR_HYPHEN=8-4 TRT_VERSION=8.4.1 TRT_VERSION_FULL=8.4.1.5 TRT_LIBNVINFER_VERSION=8.4.1 TRT_KITPICK_RC_VERSION=003 NVIDIA_TENSORRT_VERSION=8.4.1 PYVER=3.8 rm -f /usr/bin/python &&
  ln -s /usr/bin/python$PYVER /usr/bin/python
08/25/2022 8:21 PM UTC
sha256:cf86880cdcea4b411eb449cceedab26c482ba8408828609356c87376c88efdf6RUN
CUDA_VERSION=11.4.14 CUDA_VERSION_MAJOR_MINOR=11.4 CUDA_KITPICK_RC_VERSION=011 TRT_VERSION_MAJOR_MINOR_HYPHEN=8-4 TRT_VERSION=8.4.1 TRT_VERSION_FULL=8.4.1.5 TRT_LIBNVINFER_VERSION=8.4.1 TRT_KITPICK_RC_VERSION=003 NVIDIA_TENSORRT_VERSION=8.4.1 PYVER=3.8 cd ${HOME} &&
  git clone -b v2.2.3 https://github.com/pybind/pybind11.git
08/25/2022 8:21 PM UTC
sha256:1d1581245d3d529bc10b0cd471a1ed36f1e1cc327133689e0623a4e50daba94eRUN
CUDA_VERSION=11.4.14 CUDA_VERSION_MAJOR_MINOR=11.4 CUDA_KITPICK_RC_VERSION=011 TRT_VERSION_MAJOR_MINOR_HYPHEN=8-4 TRT_VERSION=8.4.1 TRT_VERSION_FULL=8.4.1.5 TRT_LIBNVINFER_VERSION=8.4.1 TRT_KITPICK_RC_VERSION=003 NVIDIA_TENSORRT_VERSION=8.4.1 PYVER=3.8 CMAKE_VERSION=3.14 &&
  CMAKE_BUILD=3.14.4 &&
  curl -L https://cmake.org/files/v${CMAKE_VERSION}/cmake-${CMAKE_BUILD}.tar.gz | tar -xzf - &&
  cd /cmake-${CMAKE_BUILD} &&
  ./bootstrap --parallel=$(nproc) --system-curl &&
  make -j"$(nproc)" install &&
  rm -rf /cmake-${CMAKE_BUILD}
08/25/2022 8:21 PM UTC
...

NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.