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=999fce674fe08a4fa6376f95d5a7772cbf327dcf`	09/22/2022 7:08 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	09/22/2022 7:08 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=44877791`	09/22/2022 7:08 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=44877791`	09/22/2022 7:08 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	09/22/2022 7:08 PM UTC
sha256:1c2a8f04e65fcf14c83c72aabbfadfbcbdc1010f52666957098631bb2f4c7122	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	09/22/2022 7:08 PM UTC
sha256:1c3c02b0ebbb6ef25af92a5e86727990a5e8e2a96777337061903d9f6aa136b3	RUN	`NVIDIA_TENSORRT_VERSION=22.09 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`	09/22/2022 7:08 PM UTC
sha256:9d2c9738b9d4e93531ed7968031d6b73fdf5e75dcfcc7c2a6b42b319dba2e01b	COPY	`README.md README.md`	09/22/2022 7:08 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	WORKDIR	`/workspace`	09/22/2022 7:08 PM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	09/22/2022 7:08 PM UTC