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=6304616c3005544d9c49b372c59237e423cfb34c`	12/14/2022 11:50 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	12/14/2022 11:50 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=49968236`	12/14/2022 11:50 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=49968236`	12/14/2022 11:50 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	12/14/2022 11:50 PM UTC
sha256:b6297d77e14ddd06394a87d7ac140a28d124bc9fa68fe24e1f22d2c3dc3ad5c5	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	12/14/2022 11:50 PM UTC
sha256:7405a394759f40524058004fed246c77fa8528f8a102c181828bdd262a752fe6	RUN	`NVIDIA_TENSORRT_VERSION=22.12 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`	12/14/2022 11:50 PM UTC
sha256:f4941d86055237a23186a0a7358654836e0639daabe624e95f915c8afcf4a8d3	COPY	`README.md README.md`	12/14/2022 11:50 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	12/14/2022 11:50 PM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	12/14/2022 11:50 PM UTC