Efficient Edge Computing: Unleashing the Potential of AI/ML with Lightweight Kubernetes
Explore the world of deploying AI and ML models in edge computing scenarios through this informative conference talk. Discover the differences between traditional cloud-based Kubernetes distributions and lightweight alternatives optimized for edge devices, such as MicroShift. Gain insights into crucial factors like power consumption, model size, and performance for successful edge deployments. Learn about serving multiple models and strategies to minimize inference process switching time in time-sensitive situations. Understand how open source components can help overcome challenges in running AI and ML models efficiently at the edge. This presentation is ideal for technology enthusiasts, developers, and industry professionals interested in leveraging the potential of AI and ML in edge computing environments.