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=1ff4894c7493e34eecba8447574693d832a08ef2`	11/21/2020 4:54 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	11/21/2020 4:54 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=17826448`	11/21/2020 4:54 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=17826448`	11/21/2020 4:54 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	11/21/2020 4:54 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENTRYPOINT	`/usr/local/bin/nvidia_entrypoint.sh`	11/21/2020 4:54 AM UTC
sha256:9a6163f2d908c709f87aef1f0bfe38221c1c248c4499781fd555b2bdf9c1bfdf	COPY	`nvidia_entrypoint.sh /usr/local/bin`	11/21/2020 4:54 AM UTC
sha256:1b5e340b283736cfe3cd09222e9d3a2466eb18b4ff8d1b0bb1b51ba61ed7ae26	RUN	`NVIDIA_TENSORRT_VERSION=20.12 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 ${_CUDA_COMPAT_PATH}/lib`	11/21/2020 4:54 AM UTC
sha256:482ded3322e96ab754acff6df1bcac014010eee5680080b5345b0beb14f737be	RUN	`NVIDIA_TENSORRT_VERSION=20.12 PYVER=3.8 (cd tensorrt && ln -s /usr/share/doc/tensorrt-${TRT_VERSION} doc && ln -s doc/pdf/TensorRT-Release-Notes.pdf .)`	11/21/2020 4:54 AM UTC
sha256:284ad2bec9f81fa649af2defcea7b70a530ba3921b62da059b88fff0c7e422da	COPY	`README.md README.md`	11/21/2020 4:54 AM UTC