Accelerating ML Inferencing with WebAssembly & Spin 2.0

By Saiyam Pathak

Elevator Pitch

In this talk Saiyam & Radu will take you through a journey exploring the transformative role of ML inferencing in the rapidly evolving field of Artificial Intelligence. The focus will be on how the integration of WebAssembly and the innovative framework, Spin 2.0, is making it easy & accessible.

Description

Join Saiyam and Radu Matei in exploring ML inferencing and AI’s evolution, focusing on WASM and Spin 2.0. The session starts with Spin 2.0, a WASM toolkit for accessible AI app development. We’ll explore its component model for robust, scalable AI applications. The talk then highlights AI inferencing with WASM, emphasizing improved performance and security, crucial for cross-platform portability. We will also discuss deploying Spin 2.0 apps on Kubernetes, demonstrating how these technologies integrate in cloud-native environments. This talk is designed for developers and AI enthusiasts, promising insights into the transformative impact of WASM and Spin 2.0 in making AI more practical and accessible. The agenda covers an introduction to Spin 2.0 for AI application development, its component model, and the use of WASM for enhanced AI inferencing. It concludes with practical insights on deploying these applications on Kubernetes, highlighting integration and operational benefits.