TiGrIS, a tiling compiler that fits ML models onto embedded devices

by Ethel Cremin

Visit

Apr 29, 2026 AI & Machine Learning

edge computing embedded systems model optimization

Gallery

About

TiGrIS is a tiling compiler designed to optimize and deploy machine learning models on embedded devices with limited memory and computational resources. It allows users to fit complex models onto smaller devices, enabling efficient inference and edge computing applications. The compiler is open-source and available on GitHub for developers to integrate into their projects.