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=aa6de835b9c7f7588b23e4ed033e6a93b371bb6f`	05/05/2022 6:59 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	05/05/2022 6:59 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=37412549`	05/05/2022 6:59 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=37412549`	05/05/2022 6:59 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	05/05/2022 6:59 PM UTC
sha256:14e8616b383a6135f9fbe8128871df4429a4e3f75dd11719d67a25996d0c72dd	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	05/05/2022 6:59 PM UTC
sha256:625e7ba014547ebe8615dabf8d1d5d073869eb65025568e72eaec47d63f0cde1	RUN	`NVIDIA_TENSORRT_VERSION=22.05 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`	05/05/2022 6:59 PM UTC
sha256:b2bdb1bff50f97ba93c83a282a3bb4e2e3895f8d131756f299192d9a5113c12e	COPY	`README.md README.md`	05/05/2022 6:59 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	WORKDIR	`/workspace`	05/05/2022 6:59 PM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	05/05/2022 6:59 PM UTC