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=f371547a75f85f4a95ae8f278a64d834776255eb`	08/17/2024 6:21 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF=f371547a75f85f4a95ae8f278a64d834776255eb`	08/17/2024 6:21 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=106933332`	08/17/2024 6:21 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=106933332`	08/17/2024 6:21 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID=106933332`	08/17/2024 6:21 AM UTC
sha256:b174367b0579ca1e7231cd671f5e4068fad24ed605a5fc8dc4d53778a3bddc7c	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	08/17/2024 6:21 AM UTC
sha256:7944bac1063cb93790af37d53c7fa62e712e7e8cd1ba67989c06dbff2232f53b	RUN	`NVIDIA_TENSORRT_VERSION=24.08 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`	08/17/2024 6:21 AM UTC
sha256:f5f0ebd8b8188da626e6f6912531b3025aa60e0e176875f08f77bd665c770fa7	COPY	`README.md README.md`	08/17/2024 6:21 AM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	08/17/2024 6:21 AM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	08/17/2024 6:21 AM UTC