WebAssembly-Based AI as a Service on the Edge with Kubernetes

Explore a cutting-edge conference talk on deploying WebAssembly-based AI as a service on edge devices using Kubernetes. Dive into the increasing adoption of WebAssembly (WASM) for edge applications and learn how WASM runtimes like WasmEdge enable serverless functions at the edge. Discover the benefits of using WebAssembly for computationally intensive Machine Learning inference tasks, and understand why Linux containers may be too heavy for such applications. Examine the limitations of standard WebAssembly in accessing native OS and hardware resources, and learn how the WebAssembly System Interface (WASI) can provide security, portability, and native speed for ML models. Conclude with a demonstration of deploying a Machine Learning model as a serverless function using WASM on an edge device, showcasing the practical implementation of these cutting-edge technologies.