Explore the latest developments in Executorch with SME2 technology and the OpenSmall model in this 47-minute technical presentation. Discover how to deploy and run Generative AI workloads using Executorch across the full spectrum of Arm-enabled devices, spanning from edge computing environments to cloud infrastructure. Learn about the technical implementation details, performance optimizations, and practical applications of these advancements from industry experts who will demonstrate real-world use cases and provide insights into the integration process. Gain understanding of how SME2 enhances Executorch capabilities and enables efficient AI inference across diverse hardware configurations, making it suitable for various deployment scenarios in modern computing environments.