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
sha256:8b6ca667fe2b96cd5a2f777221e920939e20a6d5b55c393812e8ac19d2827cf7RUN
TRT_VERSION=8.4.0.11 TRT_LIBNVINFER_VERSION=8.4.0 NVIDIA_TENSORRT_VERSION=8.4.0.11 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/python/tensorrt-$TRT_VERSION-cp38-none-linux_aarch64.whl /builds/TensorRT-$TRT_VERSION/graphsurgeon/graphsurgeon-0.4.6-py2.py3-none-any.whl /builds/TensorRT-$TRT_VERSION/python/tensorrt-$TRT_VERSION-cp${PY}-none-linux_aarch64.whl /builds/TensorRT-$TRT_VERSION/uff/uff-0.6.9-py2.py3-none-any.whl # COPY NGC-DL-CONTAINER-LICENSE /
05/04/2022 9:12 PM UTC
sha256:7ce5ba111fef717d62a6b7755f03cb70893e4b3fe44e986075ae39e8a089693bRUN
TRT_VERSION=8.4.0.11 TRT_LIBNVINFER_VERSION=8.4.0 NVIDIA_TENSORRT_VERSION=8.4.0.11 PYVER=3.8 curl -O https://bootstrap.pypa.io/get-pip.py &&
  python get-pip.py &&
  rm get-pip.py
05/04/2022 9:11 PM UTC
sha256:af2de84b8569cd4d6c1fcfb6cfd29b0dd55dcab0b38599579b2cf018bec077e6RUN
TRT_VERSION=8.4.0.11 TRT_LIBNVINFER_VERSION=8.4.0 NVIDIA_TENSORRT_VERSION=8.4.0.11 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
05/04/2022 9:11 PM UTC
sha256:4db3967e5ecfaea07569d1c910aa9ebee996a3b4754ae5f07eedd2cd67bdee2cRUN
TRT_VERSION=8.4.0.11 TRT_LIBNVINFER_VERSION=8.4.0 NVIDIA_TENSORRT_VERSION=8.4.0.11 PYVER=3.8 rm -f /usr/bin/python &&
  ln -s /usr/bin/python$PYVER /usr/bin/python
05/04/2022 9:11 PM UTC
sha256:fa72bb7463c6270f0cc98bd7f73a3aeb2495ebd350850c4faf3b050b2c795a06RUN
TRT_VERSION=8.4.0.11 TRT_LIBNVINFER_VERSION=8.4.0 NVIDIA_TENSORRT_VERSION=8.4.0.11 PYVER=3.8 rm -rf /var/lib/apt/lists/*
05/04/2022 9:11 PM UTC
sha256:4f422d6b1ef09483d52745e3cb3cac05abddb0f903c2857001216dfa924fde48RUN
TRT_VERSION=8.4.0.11 TRT_LIBNVINFER_VERSION=8.4.0 NVIDIA_TENSORRT_VERSION=8.4.0.11 PYVER=3.8 apt install -f libnvinfer8 libnvinfer-plugin8 libnvparsers8 libnvonnxparsers8 python3-libnvinfer /builds/libnvinfer-bin_${TRT_LIBNVINFER_VERSION}-1+cuda11.4_arm64.deb
05/04/2022 9:11 PM UTC
sha256:f113012a7b3b360acc01df80af687e1b718c7435dbc93d17427d988eefece6e3RUN
TRT_VERSION=8.4.0.11 TRT_LIBNVINFER_VERSION=8.4.0 NVIDIA_TENSORRT_VERSION=8.4.0.11 PYVER=3.8 apt-get update &&
  apt-get upgrade -y &&
  apt-get install -y --no-install-recommends gnupg2 curl ca-certificates &&
  curl -fsSL https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/sbsa/3bf863cc.pub | apt-key add - &&
  echo "deb  http://cuda-internal.nvidia.com/release-candidates/kitpicks/tensorrt-rel-8-4-tegra/8.4.0/004/repos/l4t/arm64 /" > /etc/apt/sources.list.d/cuda.list &&
  apt-get update &&
  apt-get install -y --no-install-recommends gnupg2 curl ca-certificates python$PYVER $DISTUTILS git pkg-config unzip
05/04/2022 9:10 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1RUN
TRT_VERSION=8.4.0.11 TRT_LIBNVINFER_VERSION=8.4.0 NVIDIA_TENSORRT_VERSION=8.4.0.11 PYVER=3.8 if [ "$PYVER" = "3.8" ]; then DISTUTILS="python3-distutils"; fi
05/04/2022 7:47 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
PYVER=3.8
05/04/2022 7:47 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
NVIDIA_TENSORRT_VERSION=8.4.0.11
05/04/2022 7:47 PM UTC