Skip to main content
NVIDIA
TensorRT
Container
NVIDIA
TensorRT

NVIDIA TensorRT is a C++ library that facilitates high-performance inference on NVIDIA graphics processing units (GPUs). TensorRT takes a trained network and produces a highly optimized runtime engine that performs inference for that network.

  • LayerLabelCreated
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4LABEL
    com.nvidia.build.ref=6b6e6b1c6d14e05e73e3fb3b88ae49cac794aa97
    02/24/2026 12:25 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    NVIDIA_BUILD_REF=6b6e6b1c6d14e05e73e3fb3b88ae49cac794aa97
    02/24/2026 12:25 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4LABEL
    com.nvidia.build.id=272060737
    02/24/2026 12:25 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    NVIDIA_BUILD_ID=272060737
    02/24/2026 12:25 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    NVIDIA_BUILD_ID=272060737
    02/24/2026 12:25 AM UTC
    sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1RUN
    NVIDIA_TENSORRT_VERSION=26.02 TRTOSS_VERSION=master PYVER=3.12 ENABLE_MITMPROXY= L4T=1 CI_JOB_TOKEN=glcbt-64_Nz199E-fHLv_EPyX5-JJ ENABLE_FIPS=0 TARGETARCH=arm64 if [ "${ENABLE_FIPS}" = "1" ] &&
      [ "${TARGETARCH}" = "amd64" ]; then echo "Running fips-fix.sh"; /tmp/fips-fix.sh; fi
    02/24/2026 12:25 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    TARGETARCH=arm64
    02/24/2026 12:25 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    ENABLE_FIPS=0
    02/24/2026 12:25 AM UTC
    sha256:9ab8985506c971336a1cc32370c53dd48f1f1f8c41fe27b0db9803862a1646efCOPY
    entrypoint.d/ /opt/nvidia/entrypoint.d/
    02/24/2026 12:25 AM UTC
    sha256:b3db99f6af4de542ce12c8cc5ae60fc02978c37ed354de723aadc63dfe45d11eRUN
    NVIDIA_TENSORRT_VERSION=26.02 TRTOSS_VERSION=master PYVER=3.12 ENABLE_MITMPROXY= L4T=1 CI_JOB_TOKEN=glcbt-64_Nz199E-fHLv_EPyX5-JJ ln -sf ${_CUDA_COMPAT_PATH}/lib.real ${_CUDA_COMPAT_PATH}/lib &&
      echo ${_CUDA_COMPAT_PATH}/lib > /etc/ld.so.conf.d/00-cuda-compat.conf &&
      ldconfig &&
      rm -f ${_CUDA_COMPAT_PATH}/lib
    02/24/2026 12:25 AM UTC
    ...

    NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.