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 2:02 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	05/02/2024 2:02 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=91390624`	05/02/2024 2:02 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=91390624`	05/02/2024 2:02 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	05/02/2024 2:02 AM UTC
sha256:a0018c9d071ce03262e4b3e76fe15e0ce4d4bc8a2082892ccfd18df3f297eb03	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	05/02/2024 2:02 AM UTC
sha256:50469cff4524ac71fb7c7bbe14dbdce799696b872e132743e8fd2397f7e98373	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 2:02 AM UTC
sha256:bc05d8f675a6063f326f00f34ffd755f6fcff8416417d35e79c492c5ce2d71ee	COPY	`README.md README.md`	05/02/2024 2:02 AM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	05/02/2024 2:02 AM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	05/02/2024 2:02 AM UTC