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=7cbec4e238c8bf7b559f14afe6f302658c3e98cc`	07/08/2024 11:48 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF=7cbec4e238c8bf7b559f14afe6f302658c3e98cc`	07/08/2024 11:48 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=100465192`	07/08/2024 11:48 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=100465192`	07/08/2024 11:48 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID=100465192`	07/08/2024 11:48 PM UTC
sha256:364ebe72887d8ec6025ac438dbd6bf8807a71dbb72182416dc8534dcfd3bad05	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	07/08/2024 11:48 PM UTC
sha256:dfabb76bba9752fa2f4f3e86d9f62e3600ab83925ab65322483c8cd32ef4de6f	RUN	`NVIDIA_TENSORRT_VERSION=24.07 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`	07/08/2024 11:48 PM UTC
sha256:26ddba19e3a992daca1d0a0d008cc393cf6e7526c211452ad8edc9fda259ba37	COPY	`README.md README.md`	07/08/2024 11:48 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	07/08/2024 11:48 PM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	07/08/2024 11:48 PM UTC