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=815747f06f190e3428667b1682a581f6a9e554ce`	09/10/2020 6:13 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	09/10/2020 6:13 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=15985252`	09/10/2020 6:13 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=15985252`	09/10/2020 6:13 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	09/10/2020 6:13 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENTRYPOINT	`/usr/local/bin/nvidia_entrypoint.sh`	09/10/2020 6:13 AM UTC
sha256:63115e6188ccfcb3725fa771a6b1130245d3f275dc2f6da859bad086531c8677	COPY	`nvidia_entrypoint.sh /usr/local/bin`	09/10/2020 6:13 AM UTC
sha256:5ac2aa7e2a84bd9c08578976e14852c74b8d7d926a9b081f78303646b7d00e10	RUN	`NVIDIA_TENSORRT_VERSION=20.09 PYVER=3.6 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 ${_CUDA_COMPAT_PATH}/lib`	09/10/2020 6:13 AM UTC
sha256:1da6ae3e0c4dba3b0f8c0e52e48ea8315353dd72855d3e40514db1849fb1bdd1	RUN	`NVIDIA_TENSORRT_VERSION=20.09 PYVER=3.6 (cd tensorrt && ln -s /usr/share/doc/tensorrt-${TRT_VERSION} doc && ln -s doc/pdf/TensorRT-Release-Notes.pdf .)`	09/10/2020 6:13 AM UTC
sha256:4d6c83e21337157c5fa4e2b66367a3078e19281e68c55de3b38c2d1655a0ec4b	COPY	`README.md README.md`	09/10/2020 6:13 AM UTC