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=c6ce9d35bd25a98d4a6cc7a8100c1b2fcc885126`	11/05/2021 2:39 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	11/05/2021 2:39 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=28968147`	11/05/2021 2:39 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=28968147`	11/05/2021 2:39 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	11/05/2021 2:39 AM UTC
sha256:83b0bf49db399b986472293fd7550d4c426a310206bd17b07d2bdae5e0ed3ee7	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	11/05/2021 2:39 AM UTC
sha256:48b446443eeb30d103e885050efbc689f1bf8abcc050fee2faf6e5520e608e05	RUN	`NVIDIA_TENSORRT_VERSION=21.11 TRTOSS_VERSION=master PYVER=3.8 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`	11/05/2021 2:39 AM UTC
sha256:cf71198c4933d542d2e6a965955f5814affccd0f59b95e18e691d230a4bc285f	COPY	`README.md README.md`	11/05/2021 2:39 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	WORKDIR	`/workspace`	11/05/2021 2:39 AM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	11/05/2021 2:39 AM UTC