Optimizing Open Models For Cross-Platform, On-Device AI Applications

NOTE: Masterclass ticket required. In this session, we'll explore practical model optimization techniques for performant, cross-platform deployment of open AI models. Learn strategies for running state-of-the-art LLMs locally, enabling the creation of privacy-focused, cost-efficient, highly scalable, and real-time AI applications. To demonstrate the power of this approach, we'll build visually stunning web applications that leverage Transformers.js to run these models on-device in the browser using emerging web technologies like WebGPU and WebNN.