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=1fd4c5898d82582ad3200af85a08a08f195b72cb`	07/02/2021 3:12 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	07/02/2021 3:12 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=24527381`	07/02/2021 3:12 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=24527381`	07/02/2021 3:12 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	07/02/2021 3:12 PM UTC
sha256:5ac931b39459e3d2e41415889d1d360ba493270f6cb0cdecee00e689c870e53e	COPY	`NVIDIA_Deep_Learning_Container_License.pdf /workspace/`	07/02/2021 3:12 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENTRYPOINT	`/usr/local/bin/nvidia_entrypoint.sh`	07/02/2021 3:12 PM UTC
sha256:bcf336e037a02eac09f08be27161ebc11d39285d3ad03dd557c2580c72499d19	COPY	`nvidia_entrypoint.sh /usr/local/bin`	07/02/2021 3:12 PM UTC
sha256:4354b3d2fc920b3ccef4a177b1b97d7cae691bb517fc387c6a493cfa9596c0c4	RUN	`NVIDIA_TENSORRT_VERSION=21.07 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`	07/02/2021 3:12 PM UTC
sha256:9ae812e0656a3d1d563e07da4f5e73111e875dfb762e305bd3d3895e4615bb62	COPY	`README.md README.md`	07/02/2021 3:12 PM UTC