Your timezone:
Wednesday, 14 May 11:00 - 11:25
(Europe/Lisbon)
Session room 3 | Opala III
KleidiAI is an optimization library designed to accelerate Machine Learning(ML) workloads for best-in-class performance on Arm CPUs. Since its inception in May 2024, it has experienced an eventful few months with integrations into multiple ML frameworks. This talk explores the integration aspects of KleidiAI into ML frameworks and how to get the best out of such integrations. We’ll discuss the ‘take-what-you-want’ tenet of the library, compare a couple of different styles of integrations and discuss how to achieve broad coverage of workloads for acceleration.
About
Felix is the technical lead of the KleidiAI library. Previously at Arm, he led optimization efforts on Cortex-M CPUs for the CMSIS-NN library. Over the years, Felix has specialized in the wireless domain, focusing on software design and optimization for memory and cycle constrained systems.