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
sha256:74976ad92a0698be558c76aaaa2340a7a1dfd482ae8cf4c79c329f3fe3face8f	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 TRT_LLM_VER=1.3.0rc25.dev2026082706 TARGETARCH=amd64 /bin/bash -c bash /tmp/gen_attribution.sh "devel" "${TRT_LLM_VER}" "${TARGETARCH}"`	08/27/2026 7:19 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TARGETARCH=amd64`	08/27/2026 7:19 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TRT_LLM_VER=1.3.0rc25.dev2026082706`	08/27/2026 7:19 AM UTC
sha256:9ffaeb2c865eb80a285aaf45c6f699977f1b42d6ce1383de10e47b9b0ac21fbf	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 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 && GITHUB_MIRROR=${GITHUB_MIRROR} bash /opt/docker/common/install_fa4.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	08/27/2026 7:19 AM UTC
sha256:d4586a948cddb315d97d820374dd2f2b19a85d13a673cf60401724bb5768f6da	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 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 numpy wandb \|\| true && rm -rf $(python3 -c "import site; print(site.getsitepackages()[0])")/nvidia_cutlass_dsl* && pip3 install -r /tmp/constraints.txt "nvidia-cutlass-dsl[cu13]==4.6.1" && rm /tmp/constraints.txt	08/27/2026 7:10 AM UTC
sha256:c9fb416a3ac4be2573e6028f60a7598f9aab2dbc181e5b7cef95d7ccfbd48ba3	COPY	`constraints.txt /tmp/constraints.txt`	08/27/2026 7:09 AM UTC
sha256:43231f6190f9772598296523405b17a2d5fb7ee3d2c73da47646003e5cc3ad5e	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: ${PYTHON_VERSION}" && GITHUB_MIRROR=${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	08/27/2026 7:09 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`TORCH_INSTALL_TYPE=skip`	08/27/2026 7:05 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`CUBLAS_VER`	08/27/2026 7:05 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NCCL_VER`	08/27/2026 7:05 AM UTC