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=65762f58f93dabf646bcbd54043ea953bf1ed8a6`	10/09/2021 1:41 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	10/09/2021 1:41 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=28007731`	10/09/2021 1:41 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=28007731`	10/09/2021 1:41 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	10/09/2021 1:41 AM UTC
sha256:1b9ca2a7f6f70ae41cb4bae841981b36dca3f89cedc141aae55402bee090cff7	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	10/09/2021 1:41 AM UTC
sha256:ff30b82de15b21cadb860cd611dc3fee4b1c2c9d5fea88f49f4f3ab9bf5af8fa	RUN	`NVIDIA_TENSORRT_VERSION=21.10 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`	10/09/2021 1:41 AM UTC
sha256:3228509a871ce7d2f602c1370923ead372449eccf11c95f092482983838716ac	COPY	`README.md README.md`	10/09/2021 1:41 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	WORKDIR	`/workspace`	10/09/2021 1:41 AM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	10/09/2021 1:41 AM UTC