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=139c8e4dd5d9d0471753a52db5a4ea2cf264e34d`	03/05/2021 11:47 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	03/05/2021 11:47 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=20572684`	03/05/2021 11:47 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=20572684`	03/05/2021 11:47 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	03/05/2021 11:47 AM UTC
sha256:fbd58224a94b3349b9f7cb10f91f4e48bd0876f141157ac1cf323dfd27d7c5df	COPY	`NVIDIA_Deep_Learning_Container_License.pdf /workspace/`	03/05/2021 11:47 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENTRYPOINT	`/usr/local/bin/nvidia_entrypoint.sh`	03/05/2021 11:47 AM UTC
sha256:0d66e744a9a0c44c5fc5358cfdb190b92aff341010b4b321efadf6e87d57a08b	COPY	`nvidia_entrypoint.sh /usr/local/bin`	03/05/2021 11:47 AM UTC
sha256:295d72c8576237d49c1612d63bfc7b9d5f1439237a8d52ee04c7b79b63656989	RUN	`NVIDIA_TENSORRT_VERSION=21.03 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`	03/05/2021 11:47 AM UTC
sha256:6513ae4c8bd60b2dfe170a86cde9691aa45765fd00bb080fae26300200566c78	COPY	`README.md README.md`	03/05/2021 11:47 AM UTC