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=846d6eddc161f4266dbf9308cef3a2244e1165f4`	03/21/2022 11:04 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	03/21/2022 11:04 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=33538116`	03/21/2022 11:04 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=33538116`	03/21/2022 11:04 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	03/21/2022 11:04 PM UTC
sha256:63d7e616a46987136f4cc9eba95db6f6327b4854cfe3c7e20fed6db0c966e380	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	03/21/2022 11:04 PM UTC
sha256:12a47450a9f9cc5d4edab65d0f600dbbe8b23a1663b0b3bb2c481d40e074b580	RUN	`NVIDIA_TENSORRT_VERSION=22.03 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`	03/21/2022 11:04 PM UTC
sha256:ef4466d6f927d29d404df9c5af3ef5733c86fa14e008762c90110b963978b1e7	COPY	`README.md README.md`	03/21/2022 11:04 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	WORKDIR	`/workspace`	03/21/2022 11:04 PM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	03/21/2022 11:04 PM UTC