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=92773cd0aee9f685f8a8da3971ae82cb44d37610`	04/05/2023 6:36 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	04/05/2023 6:36 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=57095450`	04/05/2023 6:36 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=57095450`	04/05/2023 6:36 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	04/05/2023 6:36 PM UTC
sha256:846f3b8c496ba45cce66b43f6ddf08d3742b71001111e05f8ad557c22d2514fc	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	04/05/2023 6:36 PM UTC
sha256:f03a13a6b7154a6814684a58843ea0d7ded0d3f36aae31e22cd57293320e1dc4	RUN	`NVIDIA_TENSORRT_VERSION=23.04 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`	04/05/2023 6:36 PM UTC
sha256:0757a0e6f2f5be8541a2b2e978661b58ff350d72b5d09c1cadafc85b3426cd8d	COPY	`README.md README.md`	04/05/2023 6:36 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	04/05/2023 6:36 PM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	04/05/2023 6:36 PM UTC