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=c8b44ead01d8c784d33d00f0c9b895566feb5b0f`	12/02/2021 4:50 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	12/02/2021 4:50 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=29870938`	12/02/2021 4:50 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=29870938`	12/02/2021 4:50 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	12/02/2021 4:50 AM UTC
sha256:0a80460822c0cf02908ef3e3d464080ee89ba8836bd0ea82b87f50073ff7fb69	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	12/02/2021 4:50 AM UTC
sha256:5c463831f57d00d54256f5116ddb4e30fedbe2200385df7c5c9bad9c441f3267	RUN	`NVIDIA_TENSORRT_VERSION=21.12 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`	12/02/2021 4:50 AM UTC
sha256:2c20854c8dbac342bfe7289fb1fcf76238cfccd387ac4ae5deb252cda64ba292	COPY	`README.md README.md`	12/02/2021 4:50 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	WORKDIR	`/workspace`	12/02/2021 4:50 AM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	12/02/2021 4:50 AM UTC