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:b44e194739e9271d661ba82302d55ba4d6e60e28270c7c16c6d2493ca9009bd7RUN
    GIT_COMMIT=4358fb5d5222f76ba133c3ae630aa2c06e62d073 TRT_LLM_VER=1.3.0rc22.post1 TARGETARCH=amd64 /bin/bash -c bash /mnt/gen_attribution.sh "release" "${TRT_LLM_VER}" "${TARGETARCH}"
    08/18/2026 6:24 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    TRT_LLM_GIT_COMMIT=4358fb5d5222f76ba133c3ae630aa2c06e62d073 TRT_LLM_VERSION=1.3.0rc22.post1
    08/18/2026 6:24 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    TARGETARCH=amd64
    08/18/2026 6:24 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    TRT_LLM_VER=1.3.0rc22.post1
    08/18/2026 6:24 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    GIT_COMMIT=4358fb5d5222f76ba133c3ae630aa2c06e62d073
    08/18/2026 6:24 AM UTC
    sha256:13273cb5982bd2d5a444766d6210162d69b4943fd31a991ced027527cf7846ebRUN
    /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 ./ &&
      cp -r /mnt/benchmarks ./benchmarks &&
      ln -sv $(python3 -c 'import site; print(f"{site.getsitepackages()[0]}/tensorrt_llm/libs")') lib &&
      test -f lib/libtensorrt_llm.so &&
      echo "/app/tensorrt_llm/lib" > /etc/ld.so.conf.d/tensorrt_llm.conf &&
      ldconfig &&
      ! ( ldd -v lib/libth_common.so | grep tensorrt_llm | grep -q "not found" ) &&
      rm -rf /root/.cache/uv/archive-v0 &&
      rm -rf /usr/local/lib/python3.12/dist-packages/setuptools/_vendor/jaraco.context-5.3.0.dist-info &&
      rm -rf /usr/local/lib/python3.12/dist-packages/setuptools/_vendor/wheel-0.45.1.dist-info
    08/18/2026 6:24 AM UTC
    sha256:34a6ffa1401629b7460406ad2d4e5e05de00df1d3a50eef595efe604133d9d81RUN
    /bin/bash -c TRTLLM_WHEEL=$(find /tmp/wheel -maxdepth 1 -name 'tensorrt_llm*.whl' -print -quit) &&
      test -n "${TRTLLM_WHEEL}" &&
      pip install "${TRTLLM_WHEEL}[mx]"
    08/18/2026 6:24 AM UTC
    sha256:f8f73ed25f157a0ac9a476347efa48e1726d344058f437db25f7af6bd39cd298WORKDIR
    /app/tensorrt_llm
    08/18/2026 6:21 AM UTC
    sha256:a3376484313bb1e93cd86ab2660fdc2bbf4828bc1c2a4eef9514c9259d109314RUN
    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 TRT_VER= CUDA_VER= CUDNN_VER= NCCL_VER= CUBLAS_VER= TORCH_INSTALL_TYPE=skip TRT_LLM_VER=1.3.0rc22.post1 TARGETARCH=amd64 /bin/bash -c bash /tmp/gen_attribution.sh "devel" "${TRT_LLM_VER}" "${TARGETARCH}"
    08/18/2026 6:17 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    TARGETARCH=amd64
    08/18/2026 6:17 AM UTC
    ...