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=570073186c099763ede2cc13c7db88168ccc6169`	01/24/2021 10:29 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	01/24/2021 10:29 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=19421045`	01/24/2021 10:29 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=19421045`	01/24/2021 10:29 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	01/24/2021 10:29 PM UTC
sha256:83833af4139bca2f8a4c60a05e25dd1ebb154dcb5f3f3af5003e238d20e68fb9	COPY	`NVIDIA_Deep_Learning_Container_License.pdf /workspace/`	01/24/2021 10:29 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENTRYPOINT	`/usr/local/bin/nvidia_entrypoint.sh`	01/24/2021 10:29 PM UTC
sha256:9911d052009010813ecd27caa14e0085f5d5c3b222c6cac2e784f0b2db66d027	COPY	`nvidia_entrypoint.sh /usr/local/bin`	01/24/2021 10:29 PM UTC
sha256:0e03cc0707904d8f5d7e8b018024d20b5f2761b1abf913935e81607604b8cb4a	RUN	`NVIDIA_TENSORRT_VERSION=21.02 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`	01/24/2021 10:29 PM UTC
sha256:f9174e55d386eaa26cba052c32500bb281a0467823a549a3289f1e287be22076	COPY	`README.md README.md`	01/24/2021 10:29 PM UTC