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=f406ded7ded1445a5940f0934cf083197a66774c`	04/03/2024 8:39 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	04/03/2024 8:39 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=87870608`	04/03/2024 8:39 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=87870608`	04/03/2024 8:39 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	04/03/2024 8:39 PM UTC
sha256:c1ba62984971c4a678a0aaa08971a4212539a322532d746d564bebff2b1cc99f	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	04/03/2024 8:39 PM UTC
sha256:5850e5f5faa5be5b3fa882e039572f1b2522037ea2ba6118fdcb61c6d181accb	RUN	`NVIDIA_TENSORRT_VERSION=24.04 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`	04/03/2024 8:39 PM UTC
sha256:94c8e1bc37114cf81788ddf35e6a3ef6d9577b7d983bc8d66a903d14e4980f9f	COPY	`README.md README.md`	04/03/2024 8:39 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	04/03/2024 8:39 PM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	04/03/2024 8:39 PM UTC