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=2c90da3cfe51e67fce7e5c7436384b34d8af2ecf
    08/05/2020 10:13 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    NVIDIA_BUILD_REF
    08/05/2020 10:13 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4LABEL
    com.nvidia.build.id=15268644
    08/05/2020 10:13 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    NVIDIA_BUILD_ID=15268644
    08/05/2020 10:13 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    NVIDIA_BUILD_ID
    08/05/2020 10:13 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENTRYPOINT
    /usr/local/bin/nvidia_entrypoint.sh
    08/05/2020 10:13 PM UTC
    sha256:476d403056429f23005aac00227ace4142bb9bf2cbba78d67cad9b8e01bc3e92COPY
    nvidia_entrypoint.sh /usr/local/bin
    08/05/2020 10:13 PM UTC
    sha256:750c4399967f5843160babba7a2eb2a9ad6d555b1bab4a0eae44546f9e34f693RUN
    NVIDIA_TENSORRT_VERSION=20.08 PYVER=3.6 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 ${_CUDA_COMPAT_PATH}/lib
    08/05/2020 10:13 PM UTC
    sha256:89956e1a8322bea96c25996f5ef52dd34f7ca63c97601ec029acf499b0234fd4RUN
    NVIDIA_TENSORRT_VERSION=20.08 PYVER=3.6 (cd tensorrt &&
      ln -s /usr/share/doc/tensorrt-${TRT_VERSION} doc &&
      ln -s doc/pdf/TensorRT-Release-Notes.pdf .)
    08/05/2020 10:13 PM UTC
    sha256:8e3792641d278d4ba6b0191b4dcefef1681f11aced2d8349be2282fad7db93d1COPY
    README.md README.md
    08/05/2020 10:13 PM 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.