Session: TinyML Meets PyTorch: Deploying AI at the Edge with Python Using ExecuTorch
Edge AI is transforming industries, enabling machine learning applications in resource-constrained environments like IoT devices and embedded systems. With ExecuTorch, PyTorch introduces a streamlined framework designed to meet the unique challenges of TinyML and edge AI deployments. This session provides a hands-on guide to building and optimizing edge-ready models with PyTorch and deploying them efficiently with ExecuTorch.
Attendees will explore the end-to-end workflow for creating lightweight, high-performance models for edge devices. We’ll cover techniques for model compression, optimization, and deployment while integrating ExecuTorch to achieve real-time inference on resource-limited hardware. The session concludes with a live demo showcasing the deployment of an edge-optimized AI model using ExecuTorch, highlighting its practical use in real-world scenarios.
