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=aa1a69b85993caf4ee666a4a7478be2172b6e817`	11/26/2024 4:17 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF=aa1a69b85993caf4ee666a4a7478be2172b6e817`	11/26/2024 4:17 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=125816360`	11/26/2024 4:17 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=125816360`	11/26/2024 4:17 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID=125816360`	11/26/2024 4:17 AM UTC
sha256:aec0924ca2f38b6413d29b93436fddff71e0a573aa041b9fc561f1e0bf324387	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	11/26/2024 4:17 AM UTC
sha256:b4d736869785ff4f5e56bbcbb62f453beea10d99d692ce9e6e509e02c3c4190c	RUN	`NVIDIA_TENSORRT_VERSION=24.12 TRTOSS_VERSION=master PYVER=3.12 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`	11/26/2024 4:17 AM UTC
sha256:62d524a080a65df0bff7d8a56657abdd8b27116d0d3926005c7e198c14496c2f	COPY	`README.md README.md`	11/26/2024 4:17 AM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	11/26/2024 4:17 AM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	11/26/2024 4:17 AM UTC