Skip to main content
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
    TensorRT LLM Develop
    Container
    NVIDIA
    TensorRT LLM Develop

    TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs.

  • LayerLabelCreated
    sha256:5d4321a6c00ed2801cdce75972697b9e2c85b55aef36444c615bda7b4dfbd3b4RUN
    SH_ENV=/etc/shinit_v2 BASH_ENV=/etc/bash.bashrc GITHUB_MIRROR=https://urm.nvidia.com/artifactory/github-go-remote PYTHON_VERSION=3.12.3 CUDA_VER= CUDNN_VER= NCCL_VER= CUBLAS_VER= TORCH_INSTALL_TYPE=skip GIT_COMMIT=a81da8a5a8380c4ec8c2d3eafabb8cfc55d7ad56 TRT_LLM_VER=1.4.0rc0.dev202610020600 TARGETARCH=amd64 /bin/bash -c bash /tmp/gen_attribution.sh "devel" "${TRT_LLM_VER}" "${TARGETARCH}"
    		10/02/2026 6:16 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    OMPI_ALLOW_RUN_AS_ROOT=1 OMPI_ALLOW_RUN_AS_ROOT_CONFIRM=1 PRTE_ALLOW_RUN_AS_ROOT=1 PRTE_ALLOW_RUN_AS_ROOT_CONFIRM=1
    		10/02/2026 6:16 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    TRT_LLM_GIT_COMMIT=a81da8a5a8380c4ec8c2d3eafabb8cfc55d7ad56 TRT_LLM_VERSION=1.4.0rc0.dev202610020600
    		10/02/2026 6:16 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    TARGETARCH=amd64
    		10/02/2026 6:16 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    TRT_LLM_VER=1.4.0rc0.dev202610020600
    		10/02/2026 6:16 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    GIT_COMMIT=a81da8a5a8380c4ec8c2d3eafabb8cfc55d7ad56
    		10/02/2026 6:16 AM UTC
    sha256:3197058f8faf5638d9701b9209956f9fd948e3c489b214842e628d21c5466ee8RUN
    SH_ENV=/etc/shinit_v2 BASH_ENV=/etc/bash.bashrc GITHUB_MIRROR=https://urm.nvidia.com/artifactory/github-go-remote PYTHON_VERSION=3.12.3 CUDA_VER= CUDNN_VER= NCCL_VER= CUBLAS_VER= TORCH_INSTALL_TYPE=skip /bin/bash -c . /opt/docker/common/github_auth.sh &&
  GITHUB_MIRROR=${GITHUB_MIRROR} bash /opt/docker/common/install_ucx.sh &&
  GITHUB_MIRROR=${GITHUB_MIRROR} bash /opt/docker/common/install_nixl.sh &&
  bash /opt/docker/common/install_etcd.sh &&
  rm -rf /root/.cache/uv/archive-v0 &&
  rm -rf /usr/local/lib/python3.12/dist-packages/setuptools/_vendor/jaraco.context-5.3.0.dist-info &&
  rm -rf /usr/local/lib/python3.12/dist-packages/setuptools/_vendor/wheel-*.dist-info
    		10/02/2026 6:16 AM UTC
    sha256:1c04256321c7583f170a7ab19bdca9b01f0ba8040dd901f4218c0898b77d0d38RUN
    SH_ENV=/etc/shinit_v2 BASH_ENV=/etc/bash.bashrc GITHUB_MIRROR=https://urm.nvidia.com/artifactory/github-go-remote PYTHON_VERSION=3.12.3 CUDA_VER= CUDNN_VER= NCCL_VER= CUBLAS_VER= TORCH_INSTALL_TYPE=skip /bin/bash -c if [ -n "$GITHUB_MIRROR" ]; then export PIP_INDEX_URL="https://urm.nvidia.com/artifactory/api/pypi/pypi-remote/simple"; fi &&
  pip3 uninstall -y tornado black nbconvert pillow nvidia-cutlass-dsl nvidia-cutlass-dsl-libs-base nvidia-cutlass-dsl-libs-core nvidia-cutlass-dsl-libs-cu12 nvidia-cutlass-dsl-libs-cu13 wandb ||
  true &&
  rm -rf $(python3 -c "import site; print(site.getsitepackages()[0])")/nvidia_cutlass_dsl* &&
  pip3 install -r /tmp/constraints.txt &&
  rm /tmp/constraints.txt
    		10/02/2026 6:13 AM UTC
    sha256:a5ace0efc89b1cb2aba3addc070c39442547899d51f10bc9fba302c11faae8a5COPY
    constraints.txt /tmp/constraints.txt
    		10/02/2026 6:13 AM UTC
    sha256:06152550246e2dad58302e6a225cbfca110278e49ee570a6148973487a6e4e09RUN
    SH_ENV=/etc/shinit_v2 BASH_ENV=/etc/bash.bashrc GITHUB_MIRROR=https://urm.nvidia.com/artifactory/github-go-remote PYTHON_VERSION=3.12.3 CUDA_VER= CUDNN_VER= NCCL_VER= CUBLAS_VER= TORCH_INSTALL_TYPE=skip /bin/bash -c echo "Using GitHub mirror: ${GITHUB_MIRROR}" &&
  echo "Using Python version: ${PYTHON_VERSION}" &&
  . /opt/docker/common/github_auth.sh &&
  GITHUB_MIRROR=${GITHUB_MIRROR} PYTHON_VERSION=${PYTHON_VERSION} CUDA_VER=${CUDA_VER} CUDNN_VER=${CUDNN_VER} NCCL_VER=${NCCL_VER} CUBLAS_VER=${CUBLAS_VER} TORCH_INSTALL_TYPE=${TORCH_INSTALL_TYPE} bash /opt/docker/common/install.sh --base --cmake --ccache --cuda_toolkit --cuda_libs --polygraphy --mpi4py --pytorch
    		10/02/2026 6:13 AM UTC
    ...

    Modal Content

    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.

    Manage Settings