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=dcbd5e3b6f52055788b46a9c09a5212040896748`	01/04/2024 4:02 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	01/04/2024 4:02 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=78767118`	01/04/2024 4:02 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=78767118`	01/04/2024 4:02 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	01/04/2024 4:02 AM UTC
sha256:440388cb10482fb48c4a9001656429caafa159efdc2dc841f498c681543ca681	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	01/04/2024 4:02 AM UTC
sha256:bda672d82dedf06fb8873e23f989b8a4825508a27b5fb0a83c2d52245fad2203	RUN	`NVIDIA_TENSORRT_VERSION=24.01 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`	01/04/2024 4:02 AM UTC
sha256:acc650b3d09f5effb1af92055a77f7753cff5129bc0d77d53e6067a93adf868a	COPY	`README.md README.md`	01/04/2024 4:02 AM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	01/04/2024 4:02 AM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	01/04/2024 4:02 AM UTC