NVIDIA
NVIDIA
TensorRT LLM Develop
Container
NVIDIA
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
    sha256:299ff6547f627ba7bdddd056c665077a4791990e3935137e4620f1f422afecc3RUN
    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 bash ./install_etcd.sh &&
      rm install_etcd.sh
    02/04/2026 4:24 AM UTC
    sha256:408d72c860fbbc2f95f3ca34f91de50c843164ea131f7faa409c288b4154b4e2RUN
    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=${GITHUB_MIRROR} bash ./install_nixl.sh &&
      rm install_nixl.sh
    02/04/2026 4:24 AM UTC
    sha256:1a0cefc4c919926db2a460717cc99cd7e08c33b2e897970b352947d25a851e77RUN
    GITHUB_MIRROR=https://urm.nvidia.com/artifactory/github-go-remote PYTHON_VERSION=3.12.3 TRT_VER= CUDA_VER= CUDNN_VER= NCCL_VER= CUBLAS_VER= TORCH_INSTALL_TYPE=skip /bin/bash -c GITHUB_MIRROR=${GITHUB_MIRROR} bash ./install_ucx.sh &&
      rm install_ucx.sh
    02/04/2026 4:12 AM UTC
    sha256:75347ebaba383a1e88892539468c9b55ee3aeb2b8c0227caf4868aac197612cfRUN
    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 bash ./install.sh --opencv &&
      rm install.sh
    02/04/2026 4:11 AM UTC
    sha256:3cd3c79f4e95eee12add2b14d6ed5e1a2260f88278cddd8478a48b8156f0b1ffRUN
    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 TORCH_INSTALL_TYPE=${TORCH_INSTALL_TYPE} bash ./install.sh --pytorch &&
      rm install_pytorch.sh
    02/04/2026 4:06 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    TORCH_INSTALL_TYPE=skip
    02/04/2026 4:06 AM UTC
    sha256:aadad82d7509f795f860b87941cf13f340aee7d9949fe494d3f6cfbf2e391242RUN
    GITHUB_MIRROR=https://urm.nvidia.com/artifactory/github-go-remote PYTHON_VERSION=3.12.3 TRT_VER= CUDA_VER= CUDNN_VER= NCCL_VER= CUBLAS_VER= /bin/bash -c GITHUB_MIRROR=${GITHUB_MIRROR} bash ./install.sh --mpi4py &&
      rm install_mpi4py.sh
    02/04/2026 4:06 AM UTC
    sha256:054f2a90bd571d729363ec47f56402fdb0539ff13e3890b17d806928ab315edeRUN
    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= /bin/bash -c GITHUB_MIRROR=${GITHUB_MIRROR} bash ./install.sh --polygraphy &&
      rm install_polygraphy.sh
    02/04/2026 3:53 AM UTC
    sha256:bb735392b1f5e1c393acdd40f705eadf8a3b6570d884106248fc8be6284fbd49RUN
    GITHUB_MIRROR=https://urm.nvidia.com/artifactory/github-go-remote PYTHON_VERSION=3.12.3 TRT_VER= CUDA_VER= CUDNN_VER= NCCL_VER= CUBLAS_VER= /bin/bash -c TRT_VER=${TRT_VER} CUDA_VER=${CUDA_VER} CUDNN_VER=${CUDNN_VER} NCCL_VER=${NCCL_VER} CUBLAS_VER=${CUBLAS_VER} bash ./install.sh --tensorrt &&
      rm install_tensorrt.sh
    02/04/2026 3:53 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    CUBLAS_VER
    02/04/2026 3:50 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.