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=d3c90b2b963c58875f0cd99604244a4b04ce3dc0`	03/01/2023 10:49 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	03/01/2023 10:49 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=54538654`	03/01/2023 10:49 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=54538654`	03/01/2023 10:49 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	03/01/2023 10:49 PM UTC
sha256:6e40ede8b9eb788312551ae7688d5e4691a8178dba6cd50fe4bc4f50f63171df	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	03/01/2023 10:49 PM UTC
sha256:9e3a6d3dd41c5d7c398d7b6934a644ae0be96242fbbdabc44e8dcf3e5ac40a0b	RUN	`NVIDIA_TENSORRT_VERSION=23.03 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`	03/01/2023 10:49 PM UTC
sha256:f66ff3ab1c87bc9fc004e662f765d86519f8dfdd34a18b710424ded4843b5d13	COPY	`README.md README.md`	03/01/2023 10:49 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	03/01/2023 10:49 PM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	03/01/2023 10:49 PM UTC