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
    sha256:2dd057ec69ac9e8abfb4aa33949fb99b754f015fa49329ad93a799e96c87edccRUN
    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 --upgrade --no-cache-dir "h11>=0.16" "tornado>=6.5.0" "setuptools>=78.1.1,<80" "protobuf>=4.25.8" "jupyter-core>=5.8.1"
    08/01/2025 7:05 AM UTC
    sha256:5af0eb38ca385a57893d32a48af03490cbce119812298af8353ceccc38f2f2ffRUN
    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 opencv-python-headless --force-reinstall --no-deps --no-cache-dir
    08/01/2025 7:05 AM UTC
    sha256:bed0d890a6dabe5f715bca8162909345e6595157963480d16d5b37b391c95b9bRUN
    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 opencv &&
      rm -rf /usr/local/lib/python3*/dist-packages/cv2/
    08/01/2025 7:05 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    PYTORCH_CUDA_ALLOC_CONF=garbage_collection_threshold:0.99999
    08/01/2025 7:05 AM UTC
    sha256:a599bcd2b6f52e17b873e6a52943d4b8896ac1016dfc830604176add52e64ed9RUN
    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_pytorch.sh $TORCH_INSTALL_TYPE &&
      rm install_pytorch.sh
    08/01/2025 7:05 AM UTC
    sha256:7b1bcf14ef2b58e6538915fd4ec67bc85d091aedcf3ef1397f28fe7b403fc6d3COPY
    docker/common/install_pytorch.sh install_pytorch.sh
    08/01/2025 7:05 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    TORCH_INSTALL_TYPE=skip
    08/01/2025 7:05 AM UTC
    sha256:1f741f335d9642e3071ab37493ed741e9d702bac4ec2c6afebcee78a297963f7RUN
    GITHUB_MIRROR=https://urm.nvidia.com/artifactory/github-go-remote PYTHON_VERSION=3.12.3 TRT_VER= CUDA_VER= CUDNN_VER= NCCL_VER= CUBLAS_VER= /bin/bash -c GITHUB_MIRROR=$GITHUB_MIRROR bash ./install_mpi4py.sh &&
      rm install_mpi4py.sh
    08/01/2025 7:05 AM UTC
    sha256:fc2200d958e647963a5ac0e06081de68aff83161fd8e28217f8e1ef7c1bcc00aCOPY
    docker/common/install_mpi4py.sh install_mpi4py.sh
    08/01/2025 7:04 AM UTC
    sha256:356a3ff9e40d6c157d0e8516a0bf1173705e525d71c69669fcda73cd9feb952fRUN
    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 bash ./install_polygraphy.sh &&
      rm install_polygraphy.sh
    08/01/2025 7:04 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.