NGC | Catalog

TensorRT

Logo for TensorRT
Features
Description
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.
Publisher
NVIDIA
Latest Tag
24.01-py3-igpu
Modified
February 1, 2024
Compressed Size
3.18 GB
Multinode Support
No
Multi-Arch Support
Yes
24.01-py3-igpu (Latest) Security Scan Results

Linux / arm64

Sorry, your browser does not support inline SVG.
Sorry, your browser does not support inline SVG.