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=cc89ee1a183da870999744fa5c77a5ac8ed7d740`	01/27/2023 1:28 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	01/27/2023 1:28 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=52179556`	01/27/2023 1:28 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=52179556`	01/27/2023 1:28 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	01/27/2023 1:28 AM UTC
sha256:a348d5d9574553822b114b30e30910d4e395713cff09321a2c7f22934fc3c72b	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	01/27/2023 1:28 AM UTC
sha256:a101834c51cc99028e7494851af542c656e397171302cc62753d51e4e175cad6	RUN	`NVIDIA_TENSORRT_VERSION=23.01 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`	01/27/2023 1:28 AM UTC
sha256:643f0fe7e6a7864b3da8dffe969c675006a9884863ad93757f46541eb63e1c48	COPY	`README.md README.md`	01/27/2023 1:28 AM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	01/27/2023 1:28 AM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	01/27/2023 1:28 AM UTC