ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIAKit SDK - Windows (PB25h1)NVIDIAKit SDK - Linux (PB25h1)NVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
NVIDIA
NVIDIA
NVIDIA MLPerf Inference
Container
NVIDIA
NVIDIA
NVIDIA MLPerf Inference

MLPerf Inference containers are base containers for people interested in NVIDIA's MLPerf Inference submission results

LayerLabelCreated
93482bf874c08efaa57e80834fd36abe6ba9faccb2405d1625e2675b31716da5CONFIG
WorkingDir /tmp
03/14/2023 5:43 PM UTC
0d9f4a5263bcc5c26adb70ccad973fb6483a51dbf94ba867fdfbf4336fe56092RUN
CUDA_VER=11.4 TRT_DEB_URL=http://cuda-repo/release-candidates/Libraries/TensorRT/v8.5/8.5.2.1-6ebd8d1c/11.4-r470/l4t-aarch64/deb/ TRT_MAJOR_VER=8 TRT_MINOR_VER=5 TRT_PATCH_VER=2 TRT_VER=8.5.2 ldconfig
03/14/2023 5:43 PM UTC
1d819ed2ee9a586273c3d87c0a662d490bb36915ab6e06c7aa83b85b75dc4fc8RUN
CUDA_VER=11.4 TRT_DEB_URL=http://cuda-repo/release-candidates/Libraries/TensorRT/v8.5/8.5.2.1-6ebd8d1c/11.4-r470/l4t-aarch64/deb/ TRT_MAJOR_VER=8 TRT_MINOR_VER=5 TRT_PATCH_VER=2 TRT_VER=8.5.2 install_deb_pkg() { wget -nv $TRT_DEB_URL/$1 -O $1 &&
  dpkg -i $1 &&
  rm $1; } &&
  install_deb_pkg libnvinfer${TRT_MAJOR_VER}_${TRT_VER}-1+cuda${CUDA_VER}_arm64.deb &&
  install_deb_pkg libnvinfer-dev_${TRT_VER}-1+cuda${CUDA_VER}_arm64.deb &&
  install_deb_pkg libnvinfer-plugin${TRT_MAJOR_VER}_${TRT_VER}-1+cuda${CUDA_VER}_arm64.deb &&
  install_deb_pkg libnvinfer-plugin-dev_${TRT_VER}-1+cuda${CUDA_VER}_arm64.deb &&
  install_deb_pkg libnvparsers${TRT_MAJOR_VER}_${TRT_VER}-1+cuda${CUDA_VER}_arm64.deb &&
  install_deb_pkg libnvparsers-dev_${TRT_VER}-1+cuda${CUDA_VER}_arm64.deb &&
  install_deb_pkg libnvonnxparsers${TRT_MAJOR_VER}_${TRT_VER}-1+cuda${CUDA_VER}_arm64.deb &&
  install_deb_pkg libnvonnxparsers-dev_${TRT_VER}-1+cuda${CUDA_VER}_arm64.deb &&
  install_deb_pkg python3-libnvinfer_${TRT_VER}-1+cuda${CUDA_VER}_arm64.deb &&
  install_deb_pkg python3-libnvinfer-dev_${TRT_VER}-1+cuda${CUDA_VER}_arm64.deb &&
  install_deb_pkg graphsurgeon-tf_${TRT_VER}-1+cuda${CUDA_VER}_arm64.deb &&
  install_deb_pkg uff-converter-tf_${TRT_VER}-1+cuda${CUDA_VER}_arm64.deb &&
  install_deb_pkg libnvinfer-bin_${TRT_VER}-1+cuda${CUDA_VER}_arm64.deb &&
  unset -f install_deb_pkg
03/14/2023 5:43 PM UTC
8f264d8302aea4603a6696a5a040325a33c0d50f31302dd07e29b8f2b721164fARG
TRT_VER=8.5.2
03/14/2023 5:42 PM UTC
18ebabd7ced66406b1f3d854e734931643c7f7a4ff4d94c8f1af1a2443c45d5fARG
TRT_PATCH_VER=2
03/14/2023 5:42 PM UTC
93cc19014f5cbc0cd01e7a9170e3ccd2cd25a54c3a45b5c214d6d53588d188ccARG
TRT_MINOR_VER=5
03/14/2023 5:42 PM UTC
5a5efc2b494c30f955c2c121c6de9de81e53b6a4d8a26fe1a22bf4feeb93fad8ARG
TRT_MAJOR_VER=8
03/14/2023 5:42 PM UTC
a75570e0d34cad6e873c65ab58888f9103eaa294ba54ff8bb705e566bdde7399ARG
TRT_DEB_URL=http://cuda-repo/release-candidates/Libraries/TensorRT/v8.5/8.5.2.1-6ebd8d1c/11.4-r470/l4t-aarch64/deb/
03/14/2023 5:42 PM UTC
6bee776a6340973c61cac18777ab8da8e7c38eb668ef7afeb663b8cdfa0d55c1RUN
CUDA_VER=11.4 cp /var/cudnn-local-tegra-repo-ubuntu2004-8.5.0.96/*-keyring.gpg /usr/share/keyrings/ &&
  apt update &&
  apt install -y libcudnn8*
03/14/2023 5:42 PM UTC
0130beb371f2134fd2af483cb132105cebf86d1a958b04f67e401a7575f0bed7RUN
CUDA_VER=11.4 wget -nv http://cuda-repo/release-candidates/kitpicks/cudnn-v8-5-tegra/8.5.0.96/001/local_installers/cudnn-local-tegra-repo-ubuntu2004-8.5.0.96_1.0-1_arm64.deb &&
  echo "059821695ccfa1fe8b335592b9e62765fe81d72a2525c33fbe010eaf61595c41  cudnn-local-tegra-repo-ubuntu2004-8.5.0.96_1.0-1_arm64.deb" | sha256sum --check &&
  dpkg -i ./cudnn-local-tegra-repo-ubuntu2004-8.5.0.96_1.0-1_arm64.deb &&
  rm cudnn*.deb
03/14/2023 5:37 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.