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=f946fd6f5b68d07dcc6330372428dd9b7fa4d1ec`	10/04/2023 3:29 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	10/04/2023 3:29 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=70756733`	10/04/2023 3:29 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=70756733`	10/04/2023 3:29 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	10/04/2023 3:29 AM UTC
sha256:4a86916708006845fda096f91371bd96ba94e72b4c9fd0c3cc0d5955f6ec2ffc	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	10/04/2023 3:29 AM UTC
sha256:cf414e148db377e37bd37c68c95bd2aa1b4c5fb6a97846dc5f77bff69969aef5	RUN	`NVIDIA_TENSORRT_VERSION=23.10 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`	10/04/2023 3:29 AM UTC
sha256:465f93f9dc3a681251c515fed36eeb734f64263673b746a41b3410e8611c94b9	COPY	`README.md README.md`	10/04/2023 3:29 AM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	10/04/2023 3:29 AM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	10/04/2023 3:29 AM UTC