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=ace8eb31cb4821deadf5deb762bf3d6788e79d0b`	05/02/2024 1:33 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	05/02/2024 1:33 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=91390623`	05/02/2024 1:33 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=91390623`	05/02/2024 1:33 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	05/02/2024 1:33 AM UTC
sha256:b7f1285721d25fe6b633372bf7a71b7c78e2e716a21d48f576f54fade5b6b3ab	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	05/02/2024 1:33 AM UTC
sha256:2cd3c44f8c51fff9766310d020aafa21a9b5511b751c2d7f9fea714a5f87758d	RUN	`NVIDIA_TENSORRT_VERSION=24.05 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`	05/02/2024 1:33 AM UTC
sha256:8b3903d07c31233a6e3ef9e04ac25057e70073dbad10d015f8bbaf3c0b7f00a3	COPY	`README.md README.md`	05/02/2024 1:33 AM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	05/02/2024 1:33 AM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	05/02/2024 1:33 AM UTC