ExecuTorch, Meta’s open source, lightweight, and efficient inference engine, has been instrumental in enabling on-device AI capabilities across Meta’s...

Meta AI's platform is a resource for artificial intelligence (AI) researchers, machine learning practitioners, and technology enthusiasts. Through articles, research papers, and technical discussions, Meta AI offers insights into AI algorithms, deep learning models, and neural network architectures. Readers can learn about AI applications in various domains, such as computer vision, natural language processing, and reinforcement learning. Additionally, Meta AI provides updates on the latest advancements in AI research, AI ethics, and AI governance to help readers stay informed and engaged in the rapidly evolving field of artificial intelligence.

AI at Meta

ExecuTorch is Meta's open source inference engine that enables on-device AI across Reality Labs products including Quest 3, Quest 3S, and Ray-Ban Meta glasses. The PyTorch-native framework eliminates model conversion steps, allowing developers to validate optimizations before deployment while maintaining consistent performance across different hardware. Key applications include real-time hand tracking, room memory for VR headsets, and live translation with visual captions for AR glasses. The project has grown into a collaborative ecosystem with contributions from major hardware partners like Apple, Arm, Qualcomm, and Samsung.

ExecuTorch Adoption in Reality Labs: Powering On-Device AI Across Meta Devices