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=ac329e3a80e1dbae4230001a076738a48519eda3
    07/31/2020 8:10 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    NVIDIA_BUILD_REF
    07/31/2020 8:10 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4LABEL
    com.nvidia.build.id=15171959
    07/31/2020 8:10 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    NVIDIA_BUILD_ID=15171959
    07/31/2020 8:10 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    NVIDIA_BUILD_ID
    07/31/2020 8:10 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENTRYPOINT
    /usr/local/bin/nvidia_entrypoint.sh
    07/31/2020 8:10 PM UTC
    sha256:e0df5a2506a816392b7ee0b7c4bdb4550e19c2a9d62b67032b158668700387d0COPY
    nvidia_entrypoint.sh /usr/local/bin
    07/31/2020 8:10 PM UTC
    sha256:95b073e3c5a765448d4a10cccb3b0e3c678358dba1a1da38fc82396f4194e95cRUN
    NVIDIA_TENSORRT_VERSION=20.07.1 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 ${_CUDA_COMPAT_PATH}/lib
    07/31/2020 8:10 PM UTC
    sha256:7847f6ea942d098f787965e566cbf414000b6cffa7c87b6b0ac4d696e3533d66RUN
    NVIDIA_TENSORRT_VERSION=20.07.1 PYVER=3.6 (cd tensorrt &&
      ln -s /usr/share/doc/tensorrt-${TRT_VERSION} doc &&
      ln -s doc/pdf/TensorRT-Release-Notes.pdf .)
    07/31/2020 8:10 PM UTC
    sha256:e8d47bf585f6eaca56b8a6a45091373607ecb2f69ae54a29e9369ed0db725f56COPY
    README.md README.md
    07/31/2020 8:10 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.