Skip to main content
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
    sha256:45d5f57260350bac87960fd1c4c80ad99d0a1289f979ace73d8baaf1f29e3361RUN
    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 TRT_VER= CUDA_VER= CUDNN_VER= NCCL_VER= CUBLAS_VER= TORCH_INSTALL_TYPE=skip TRT_LLM_VER=1.3.0rc8 TARGETARCH=amd64 /bin/bash -c bash /tmp/generate_container_oss_attribution.sh "devel" "${TRT_LLM_VER}" "${TARGETARCH}" &&
      rm /tmp/generate_container_oss_attribution.sh
    03/16/2026 6:41 AM UTC
    sha256:85c95ca10c80f53fc9295f2b1a2f2bac2389d8d5ee0933ef5254acba3aa7b148COPY
    scripts/generate_container_oss_attribution.sh /tmp/generate_container_oss_attribution.sh
    03/16/2026 6:41 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    TARGETARCH=amd64
    03/16/2026 6:41 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    TRT_LLM_VER=1.3.0rc8
    03/16/2026 6:41 AM UTC
    sha256:1b290a0ef13cf5128b99fd6b7aa30e98773c0644289b9363ac6fd4ac262bfb37RUN
    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 TRT_VER= CUDA_VER= CUDNN_VER= NCCL_VER= CUBLAS_VER= TORCH_INSTALL_TYPE=skip /bin/bash -c GITHUB_MIRROR=${GITHUB_MIRROR} bash ./install_ucx.sh &&
      GITHUB_MIRROR=${GITHUB_MIRROR} bash ./install_nixl.sh &&
      bash ./install_etcd.sh &&
      rm install_ucx.sh &&
      rm install_nixl.sh &&
      rm install_etcd.sh &&
      rm -rf /root/.cache/pip &&
      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-0.45.1.dist-info
    03/16/2026 6:41 AM UTC
    sha256:ae18c7fe22319100f39bfc1f16599206ee9448b4cf54ee243cf25b6ce572693aRUN
    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 TRT_VER= CUDA_VER= CUDNN_VER= NCCL_VER= CUBLAS_VER= TORCH_INSTALL_TYPE=skip /bin/bash -c pip3 uninstall -y nbconvert ||
      true
    03/16/2026 6:39 AM UTC
    sha256:803029c10d16cc2f0e8083ff2b4c581d97475d31b11698dedc2adf601bb237cbRUN
    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 TRT_VER= CUDA_VER= CUDNN_VER= NCCL_VER= CUBLAS_VER= TORCH_INSTALL_TYPE=skip /bin/bash -c pip3 install --no-cache-dir -r /tmp/constraints.txt &&
      rm /tmp/constraints.txt
    03/16/2026 6:39 AM UTC
    sha256:bcad7d742453877b2cc33d6b53e73e34915b208b24c5dc050c23dbe103ca40e6COPY
    constraints.txt /tmp/constraints.txt
    03/16/2026 6:39 AM UTC
    sha256:e6cb5dc76dc5b70bf850ecbd967ebcce00cb8d5d001325f4233e664aa9ead1dcRUN
    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 TRT_VER= CUDA_VER= CUDNN_VER= NCCL_VER= CUBLAS_VER= TORCH_INSTALL_TYPE=skip /bin/bash -c GITHUB_MIRROR=${GITHUB_MIRROR} PYTHON_VERSION=${PYTHON_VERSION} TRT_VER=${TRT_VER} CUDA_VER=${CUDA_VER} CUDNN_VER=${CUDNN_VER} NCCL_VER=${NCCL_VER} CUBLAS_VER=${CUBLAS_VER} TORCH_INSTALL_TYPE=${TORCH_INSTALL_TYPE} bash ./install.sh --base --cmake --ccache --cuda_toolkit --tensorrt --polygraphy --mpi4py --pytorch --opencv &&
      rm install_base.sh &&
      rm install_cmake.sh &&
      rm install_ccache.sh &&
      rm install_cuda_toolkit.sh &&
      rm install_tensorrt.sh &&
      rm install_polygraphy.sh &&
      rm install_mpi4py.sh &&
      rm install_pytorch.sh &&
      rm install.sh
    03/16/2026 6:39 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    TORCH_INSTALL_TYPE=skip
    03/16/2026 6:35 AM 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.