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=5e5d03a41ad605010461691dc37f0388c58b4b15`	02/10/2024 12:11 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	02/10/2024 12:11 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=82396605`	02/10/2024 12:11 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=82396605`	02/10/2024 12:11 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	02/10/2024 12:11 AM UTC
sha256:8fcfb88286574948f0dded2b5d0a328d365a124d64f8165230080c6dca5a72b2	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	02/10/2024 12:11 AM UTC
sha256:ef45f51f86585166507865c8fd1d4dc1cbbaf3f1d6a39aab0c38f4e55e0d614a	RUN	`NVIDIA_TENSORRT_VERSION=24.02 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`	02/10/2024 12:11 AM UTC
sha256:971ab13d836dc1dacaafab93a36800baa5aaec9b9f7fdcc3318b6a91cdb9024a	COPY	`README.md README.md`	02/10/2024 12:11 AM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	02/10/2024 12:11 AM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	02/10/2024 12:11 AM UTC