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=666290aba68a2660d93eddacdd2a6345b7cc2604`	08/02/2021 6:17 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	08/02/2021 6:17 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=25497161`	08/02/2021 6:17 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=25497161`	08/02/2021 6:17 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	08/02/2021 6:17 PM UTC
sha256:137f3a1f960009f4177161219e23e727cd09ec8ed66a791f98f5b348c518e792	COPY	`NVIDIA_Deep_Learning_Container_License.pdf /workspace/`	08/02/2021 6:17 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENTRYPOINT	`/usr/local/bin/nvidia_entrypoint.sh`	08/02/2021 6:17 PM UTC
sha256:655e84e7e87d6498ff4314ca74e1c6001daa665058ece1f37cec83285adc1dd4	COPY	`nvidia_entrypoint.sh /usr/local/bin`	08/02/2021 6:17 PM UTC
sha256:3d4579340e73e69afcce2ee393d88f64693b59d075ce9c3ef7c2f31c8a6685c8	RUN	`NVIDIA_TENSORRT_VERSION=21.08 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`	08/02/2021 6:17 PM UTC
sha256:3c4726dac2c369999b5e896944c4dcce7fc99bbf1e95b59ffaf26acac06e92db	COPY	`README.md README.md`	08/02/2021 6:17 PM UTC