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=c9937be0eb86fd57554377023209f717cae6fc1b`	09/06/2023 6:47 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	09/06/2023 6:47 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=68471706`	09/06/2023 6:47 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=68471706`	09/06/2023 6:47 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	09/06/2023 6:47 AM UTC
sha256:42a41623f4d71f6d026da00d03cc8778b09d84939a7b153e669c3e83d56884c2	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	09/06/2023 6:47 AM UTC
sha256:088befa2ee21436750297bdfc7ed5d0955148b425444a461bc2dcd269c23691d	RUN	`NVIDIA_TENSORRT_VERSION=23.09 TRTOSS_VERSION=master PYVER=3.10 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`	09/06/2023 6:47 AM UTC
sha256:d7ec94f0ee61368489508cf316503effd82862d9bf4857526d58ef152b0cb856	COPY	`README.md README.md`	09/06/2023 6:47 AM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	09/06/2023 6:47 AM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	09/06/2023 6:47 AM UTC