TensorRT | NVIDIA NGC

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.

NVIDIA AI Enterprise Supported

Layer	Label		Created
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.ref=29ce4cb9f904e0ea3b53ddd8ba836869b81d16e9`	06/06/2020 7:12 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	06/06/2020 7:12 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=13239395`	06/06/2020 7:12 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=13239395`	06/06/2020 7:12 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	06/06/2020 7:12 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENTRYPOINT	`/usr/local/bin/nvidia_entrypoint.sh`	06/06/2020 7:12 PM UTC
sha256:4c50d7c76a807e11769c4007811a936b39767aae7bf04993270546ed214ec89f	COPY	`nvidia_entrypoint.sh /usr/local/bin`	06/06/2020 7:12 PM UTC
sha256:7b057e728811356368de461d4cf85927e032cb61717825447a9e39d40b23de67	RUN	`NVIDIA_TENSORRT_VERSION=20.06 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 ${_CUDA_COMPAT_PATH}/lib`	06/06/2020 7:12 PM UTC
sha256:4feee54921f9a39e894d282a046d7fc25ce6c3ba3aa5e3dcc679a5f2d0dba572	RUN	`NVIDIA_TENSORRT_VERSION=20.06 PYVER=3.6 (cd tensorrt && ln -s /usr/share/doc/tensorrt-${TRT_VERSION} doc && ln -s doc/pdf/TensorRT-Release-Notes.pdf .)`	06/06/2020 7:12 PM UTC
sha256:3acb89bc9b18bace65182c313a23d1fbb22c6109d1b8ecccbc645489bc7cee64	COPY	`README.md README.md`	06/06/2020 7:12 PM UTC