Supercharge ML and Inference on Apple Silicon with EC2 Mac

Explore how to accelerate machine learning workflows and inference using EC2 Mac instances powered by Apple silicon in this 50-minute conference talk from AWS re:Invent 2025. Learn to harness the Apple Neural Engine (ANE) and Core ML framework to supercharge your ML performance while reducing development and operational costs. Discover practical techniques for efficiently deploying PyTorch and TensorFlow models on M-series chips, with specific optimization strategies tailored for Apple silicon architecture. Gain insights into leveraging EC2 Mac instances for both iOS development workflows and cloud-native machine learning applications, understanding how to unlock the full potential of Apple's hardware acceleration capabilities directly from AWS cloud infrastructure.