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=72050591d51c5a1c4565c8833b07657cd83ab97d`	08/04/2022 5:10 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	08/04/2022 5:10 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=42105201`	08/04/2022 5:10 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=42105201`	08/04/2022 5:10 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	08/04/2022 5:10 AM UTC
sha256:c8278b608f3c5fc5912653e06a8fb7121f6413df0430ceef453e2c013399ea21	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	08/04/2022 5:10 AM UTC
sha256:35fd5868fa9428a15de6de1f3983cc852272f57d0392360ef1ec5411e9ed65a2	RUN	`NVIDIA_TENSORRT_VERSION=22.08 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`	08/04/2022 5:10 AM UTC
sha256:64db64b55e17de51b504fdee855a523b546d6f26fd42d1f93c79f4584ec955bf	COPY	`README.md README.md`	08/04/2022 5:10 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	WORKDIR	`/workspace`	08/04/2022 5:10 AM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	08/04/2022 5:10 AM UTC