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=c265f243f34c81fe85e6ce4522f68bb176ac3ca1`	07/06/2023 7:46 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	07/06/2023 7:46 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=63868013`	07/06/2023 7:46 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=63868013`	07/06/2023 7:46 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	07/06/2023 7:46 PM UTC
sha256:b5d95c839e6cb8762cd64cd18be149ecf2e625a4bfb3b36182909c0ed0c83501	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	07/06/2023 7:46 PM UTC
sha256:befe5dd5dfa184baadc00d5f0c0add92dfefd18d4de988c52e9680a9df90f509	RUN	`NVIDIA_TENSORRT_VERSION=23.07 TRTOSS_VERSION=master PYVER=3.10 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`	07/06/2023 7:46 PM UTC
sha256:d10c2f400e1d122d848110a818ee66f57cb9547216c92d7cadb62a92c5c41f96	COPY	`README.md README.md`	07/06/2023 7:46 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	07/06/2023 7:46 PM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	07/06/2023 7:46 PM UTC