NVIDIA
NVIDIA
TensorRT LLM Release
Container
NVIDIA
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
sha256:145813d020c55d3dedae41ac6cec81d9d57a3eb350a3765efe6f11a05afef577RUN
GIT_COMMIT=8ba93401976877ca2a390104829dd0d54cf2f30f TRT_LLM_VER=1.3.0rc22 TARGETARCH=amd64 /bin/bash -c bash /mnt/gen_attribution.sh "release" "${TRT_LLM_VER}" "${TARGETARCH}"
07/20/2026 11:35 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
TRT_LLM_GIT_COMMIT=8ba93401976877ca2a390104829dd0d54cf2f30f TRT_LLM_VERSION=1.3.0rc22
07/20/2026 11:35 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
TARGETARCH=amd64
07/20/2026 11:35 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
TRT_LLM_VER=1.3.0rc22
07/20/2026 11:35 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
GIT_COMMIT=8ba93401976877ca2a390104829dd0d54cf2f30f
07/20/2026 11:35 PM UTC
sha256:bb69230fbff65742347297f8a8d5481a1e152beaf941da4e0399319fd133560fRUN
/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 $(python3 -c 'import site; print(f"{site.getsitepackages()[0]}/tensorrt_llm/libs")') lib &&
  test -f lib/libtensorrt_llm.so &&
  echo "/app/tensorrt_llm/lib" > /etc/ld.so.conf.d/tensorrt_llm.conf &&
  ldconfig &&
  ! ( ldd -v lib/libth_common.so | grep tensorrt_llm | grep -q "not found" ) &&
  rm -rf /root/.cache/uv/archive-v0 &&
  rm -rf /usr/local/lib/python3.12/dist-packages/setuptools/_vendor/jaraco.context-5.3.0.dist-info &&
  rm -rf /usr/local/lib/python3.12/dist-packages/setuptools/_vendor/wheel-0.45.1.dist-info
07/20/2026 11:35 PM UTC
sha256:00a3777c7ec26ec1b8ab420639211470c32a301609109908f50cb83b57222bbfRUN
/bin/bash -c TRTLLM_WHEEL=$(find /tmp/wheel -maxdepth 1 -name 'tensorrt_llm*.whl' -print -quit) &&
  test -n "${TRTLLM_WHEEL}" &&
  pip install "${TRTLLM_WHEEL}[mx]"
07/20/2026 11:35 PM UTC
sha256:efab65437fea0924b57869f0f4912ca73396cab79e838b1da910ed0a8d28cac9WORKDIR
/app/tensorrt_llm
07/20/2026 11:23 PM UTC
sha256:29ce6d6168256daedd7ffe9733130c7847f11713df8852e5f968cd54968a01f3RUN
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 TARGETARCH=amd64 /bin/bash -c bash /tmp/gen_attribution.sh "devel" "${TRT_LLM_VER}" "${TARGETARCH}"
07/20/2026 11:18 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
TARGETARCH=amd64
07/20/2026 11:18 PM UTC
...