TensorRT LLM Develop

NVIDIA

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.

Layer	Label		Created
sha256:ca2318ee00553b882d78f8b60d1551c556b0fa4427fd9b88790172c80dad2c48	RUN	`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=fca831eac3da515461e148b05e0663c29ab6aaa5 TRT_LLM_VER=1.3.0rc28 TARGETARCH=amd64 /bin/bash -c bash /tmp/gen_attribution.sh "devel" "${TRT_LLM_VER}" "${TARGETARCH}"`	09/21/2026 2:27 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`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`	09/21/2026 2:27 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`TRT_LLM_GIT_COMMIT=fca831eac3da515461e148b05e0663c29ab6aaa5 TRT_LLM_VERSION=1.3.0rc28`	09/21/2026 2:27 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TARGETARCH=amd64`	09/21/2026 2:27 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TRT_LLM_VER=1.3.0rc28`	09/21/2026 2:27 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`GIT_COMMIT=fca831eac3da515461e148b05e0663c29ab6aaa5`	09/21/2026 2:27 PM UTC
sha256:be544706ff0136f8db6fbe1a243cb785ef938e163d7c0025a97b7612d330c82c	RUN	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	09/21/2026 2:27 PM UTC
sha256:9842278906e993008f68fad4135c9e5c5e70c481e002e4313a9de20410962e44	RUN	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	09/21/2026 2:23 PM UTC
sha256:a7829923f979c5a83be1e53b76987be00e0d8dd6d75b9bb8de99a366c76a8040	COPY	`constraints.txt /tmp/constraints.txt`	09/21/2026 2:23 PM UTC
sha256:5b1e49207b6a9d1d817f599e1dca430b67b533d288593200fde93dafcd7e9ed0	RUN	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	09/21/2026 2:23 PM UTC