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=53ab9aa64e5209dbb42780f78f39e3c2c12e8858`	01/07/2022 4:42 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	01/07/2022 4:42 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=30856447`	01/07/2022 4:42 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=30856447`	01/07/2022 4:42 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	01/07/2022 4:42 PM UTC
sha256:023723e94b4d285a07728ca9cc6ab6c2344f46b329e34e2f6c6fc1ed6d1819de	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	01/07/2022 4:42 PM UTC
sha256:bbbc92f87ffab8795bcb1ea006f15e5e1de835ca465a6df97034727c266e3d57	RUN	`NVIDIA_TENSORRT_VERSION=22.01 TRTOSS_VERSION=master PYVER=3.8 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`	01/07/2022 4:42 PM UTC
sha256:4d4e7be7dcd1e885c5de2c8f00f1ef9e07cac89070376d15e15016a8be5cb5c2	COPY	`README.md README.md`	01/07/2022 4:42 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	WORKDIR	`/workspace`	01/07/2022 4:42 PM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	01/07/2022 4:42 PM UTC