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:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
TRT_LLM_GIT_COMMIT=a30d3b7419840e185070b05f67f3d76a2f54c894 TRT_LLM_VERSION=1.2.0rc2.post1
01/05/2026 8:48 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
TRT_LLM_VER=1.2.0rc2.post1
01/05/2026 8:48 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
GIT_COMMIT=a30d3b7419840e185070b05f67f3d76a2f54c894
01/05/2026 8:48 AM UTC
sha256:ea39f63449544d165884a6199ac932372c2ae45f447fb22fee597ce1b17f955bRUN
SRC_DIR=/src/tensorrt_llm CPP_BUILD_DIR=/src/tensorrt_llm/cpp/build /bin/bash -c chmod -R a+w examples &&
  rm -v benchmarks/cpp/bertBenchmark.cpp benchmarks/cpp/gptManagerBenchmark.cpp benchmarks/cpp/disaggServerBenchmark.cpp benchmarks/cpp/CMakeLists.txt &&
  rm -rf /root/.cache/pip
01/05/2026 8:48 AM UTC
sha256:6a77220351ecb2ccf47da2e638701cf7f8bc8ba0483533da5a4c820dcfa910e1COPY
examples examples
01/05/2026 8:48 AM UTC
sha256:931f917275da7b3f176c612bb46cc63c44af495b102194537c36d11f9e31cbe5COPY
/src/tensorrt_llm/cpp/build/benchmarks/bertBenchmark /src/tensorrt_llm/cpp/build/benchmarks/gptManagerBenchmark /src/tensorrt_llm/cpp/build/benchmarks/disaggServerBenchmark benchmarks/cpp/
01/05/2026 8:48 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
CPP_BUILD_DIR=/src/tensorrt_llm/cpp/build
01/05/2026 8:48 AM UTC
sha256:5f16d738d78b7e4a2a1c0e34ddb37350378ccf1d4d76dbc6d37f2604d8a03079COPY
/src/tensorrt_llm/benchmarks benchmarks
01/05/2026 8:48 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
SRC_DIR=/src/tensorrt_llm
01/05/2026 8:48 AM UTC
sha256:9a41e73dc343a32f042ee4358f9e31cb473574b7a4af854ef4e14c104099727bRUN
/bin/bash -c ln -sv $(python3 -c 'import site; print(f"{site.getsitepackages()[0]}/tensorrt_llm/bin")') bin &&
  test -f bin/executorWorker &&
  ln -sv $(python3 -c 'import site; print(f"{site.getsitepackages()[0]}/tensorrt_llm/libs")') lib &&
  test -f lib/libnvinfer_plugin_tensorrt_llm.so &&
  echo "/app/tensorrt_llm/lib" > /etc/ld.so.conf.d/tensorrt_llm.conf &&
  ldconfig &&
  ! ( ldd -v bin/executorWorker | grep tensorrt_llm | grep -q "not found" )
01/05/2026 8:48 AM UTC
...