Sponsored Session: Lightning Talk: Accelerating Experimentation and Unlocking Real-Time Inference on Microcontrollers with Lightning - Niall Lyons, Infineon Technologies & Luca Antiga, Lightning AI
Join Luca Antiga, CTO of Lightning AI and early PyTorch core contributor, and Niall Lyons, Staff Deep Learning Researcher at Infineon Technologies.Learn first-hand how the Lightning platform streamlines model training and optimized inference by handling environment setup, scaling across heterogeneous hardware, and enabling rapid experimentation. Infineon will share how they applied Lightning to train and deploy sub 30MB language models on Cortex M55 and U55 microcontrollers, achieving inference under 100ms per token fully on device with no external compute. Learn how the Lightning platform enabled the Infineon team to accelerate experimentation and unlock real-time AI inference at the edge.