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=ed48bc20184dc90266d3fe45955f9b5a330b65b3`	10/28/2020 9:27 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	10/28/2020 9:27 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=17147175`	10/28/2020 9:27 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=17147175`	10/28/2020 9:27 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	10/28/2020 9:27 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENTRYPOINT	`/usr/local/bin/nvidia_entrypoint.sh`	10/28/2020 9:27 PM UTC
sha256:0a6de8981ce911ff2a8f284c8ee63d886c45dd7efeebaf53f1aa1eb07d5f4225	COPY	`nvidia_entrypoint.sh /usr/local/bin`	10/28/2020 9:27 PM UTC
sha256:11096700ede2301e840fbf03ba46b4ecdef96dcaf26121a63fc8358ed535e0ed	RUN	`NVIDIA_TENSORRT_VERSION=20.11 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 ${_CUDA_COMPAT_PATH}/lib`	10/28/2020 9:27 PM UTC
sha256:f0ffbc7e0edadc0955e7cfc073d0082768bebb2f8d03c5e82652aac3489dbcb6	RUN	`NVIDIA_TENSORRT_VERSION=20.11 PYVER=3.6 (cd tensorrt && ln -s /usr/share/doc/tensorrt-${TRT_VERSION} doc && ln -s doc/pdf/TensorRT-Release-Notes.pdf .)`	10/28/2020 9:27 PM UTC
sha256:a039ec5ed3d96d95a1b6ae69954d9e4cbd698296e669981fa817202ac9c556a0	COPY	`README.md README.md`	10/28/2020 9:27 PM UTC