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=2cf8cc0ece6287232f7e80de94cbbf2e8dff6345`	04/23/2021 1:41 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	04/23/2021 1:41 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=22393618`	04/23/2021 1:41 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=22393618`	04/23/2021 1:41 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	04/23/2021 1:41 AM UTC
sha256:6b20111bcfdc4996ae85aba7c22cb37e7e5f267229801e5c072aa66c83243351	COPY	`NVIDIA_Deep_Learning_Container_License.pdf /workspace/`	04/23/2021 1:41 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENTRYPOINT	`/usr/local/bin/nvidia_entrypoint.sh`	04/23/2021 1:41 AM UTC
sha256:ed67b177252632d07826d8cd4a57f905abca5b677ea3086d3ee96d4dcf1f9fd0	COPY	`nvidia_entrypoint.sh /usr/local/bin`	04/23/2021 1:41 AM UTC
sha256:1b226eccb262cb266175f00c68e70be3c63d18f2941fdf49812d9d1f1821be5b	RUN	`NVIDIA_TENSORRT_VERSION=21.04 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`	04/23/2021 1:41 AM UTC
sha256:35d9682f4ab9ddef62e7654384ca43d8adedbfea446380f6ff7d99fb6537565e	COPY	`README.md README.md`	04/23/2021 1:41 AM UTC