NVIDIA
TensorRT LLM Release
Container
NVIDIA
TensorRT LLM Release

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
    sha256:9fed02e781270690655b929c38b911279c7c0da3ff53a2f12f8f04f2fdf35b0bRUN
    GITHUB_MIRROR=https://urm.nvidia.com/artifactory/github-go-remote GIT_COMMIT=7e106301dfc5714cfc8694b336ac1fb91f2abb0c TRT_LLM_VER=1.3.0rc25.dev2026082600 TARGETARCH=amd64 /bin/bash -c bash /mnt/gen_attribution.sh "release" "${TRT_LLM_VER}" "${TARGETARCH}"
    08/26/2026 12:21 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    TRT_LLM_GIT_COMMIT=7e106301dfc5714cfc8694b336ac1fb91f2abb0c TRT_LLM_VERSION=1.3.0rc25.dev2026082600
    08/26/2026 12:21 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    TARGETARCH=amd64
    08/26/2026 12:21 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    TRT_LLM_VER=1.3.0rc25.dev2026082600
    08/26/2026 12:21 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    GIT_COMMIT=7e106301dfc5714cfc8694b336ac1fb91f2abb0c
    08/26/2026 12:21 AM UTC
    sha256:d7174980b99efd9e60812fd33d16374c2605a824210a537423bc1a7dddb7633eRUN
    GITHUB_MIRROR=https://urm.nvidia.com/artifactory/github-go-remote /bin/bash -c cp /mnt/ctx/README.md ./ &&
      cp -r /mnt/ctx/docs ./docs &&
      cp -r /mnt/ctx/include ./include &&
      cp -r /mnt/ctx/examples ./examples &&
      chmod -R a+w examples &&
      cp /mnt/wheel/tensorrt_llm*.whl ./ &&
      ln -sv $(python3 -c 'import site; print(f"{site.getsitepackages()[0]}/tensorrt_llm/libs")') lib &&
      test -f lib/libtensorrt_llm.so &&
      echo "/app/tensorrt_llm/lib" > /etc/ld.so.conf.d/tensorrt_llm.conf &&
      ldconfig &&
      ! ( ldd -v lib/libth_common.so | grep tensorrt_llm | grep -q "not found" ) &&
      rm -rf /root/.cache/uv/archive-v0 &&
      rm -rf /usr/local/lib/python3.12/dist-packages/setuptools/_vendor/jaraco.context-5.3.0.dist-info &&
      rm -rf /usr/local/lib/python3.12/dist-packages/setuptools/_vendor/wheel-0.45.1.dist-info
    08/26/2026 12:21 AM UTC
    sha256:152acbee7ee6890a331a8e8ca9bb2dd49edbd1d304128daaf3c54bd4352edb65RUN
    GITHUB_MIRROR=https://urm.nvidia.com/artifactory/github-go-remote /bin/bash -c if [ -n "$GITHUB_MIRROR" ]; then export PIP_INDEX_URL="https://urm.nvidia.com/artifactory/api/pypi/pypi-remote/simple"; fi &&
      TRTLLM_WHEEL=$(find /tmp/wheel -maxdepth 1 -name 'tensorrt_llm*.whl' -print -quit) &&
      test -n "${TRTLLM_WHEEL}" &&
      pip install "${TRTLLM_WHEEL}[mx]"
    08/26/2026 12:21 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    GITHUB_MIRROR=https://urm.nvidia.com/artifactory/github-go-remote
    08/26/2026 12:21 AM UTC
    sha256:fdff800b926e17dfae1e13fbbff69ad989217214138a076df9ed94bac177297cWORKDIR
    /app/tensorrt_llm
    08/26/2026 12:19 AM UTC
    sha256:24f3c7ac8910fe26a70bc3a9393daf72e2d130b5cd5bf5e84ac1e3706e281a6cRUN
    SH_ENV=/etc/shinit_v2 BASH_ENV=/etc/bash.bashrc GITHUB_MIRROR=https://urm.nvidia.com/artifactory/github-go-remote PYTHON_VERSION=3.12.3 CUDA_VER= CUDNN_VER= NCCL_VER= CUBLAS_VER= TORCH_INSTALL_TYPE=skip TRT_LLM_VER=1.3.0rc25.dev2026082600 TARGETARCH=amd64 /bin/bash -c bash /tmp/gen_attribution.sh "devel" "${TRT_LLM_VER}" "${TARGETARCH}"
    08/26/2026 12:17 AM UTC
    ...