WebAssembly Based AI as a Service on the Edge with Kubernetes
Talkat Kubernetes on Edge Day North America 2022 · on Tuesday, 2022-10-25· at 09:50· Room 250 ABC, Huntington Place: 1 Washington Blvd·
summary
Shows a concrete pipeline: Rust code compiles to a .wasm module, optionally AOT‑compiled with WasmEdge to native, runs TensorFlow Lite MobileNetV2 inference inside WASI, and deploys as an OCI image on Kubernetes using containerd shim and Spin. Demo runs on an Azure cluster with two node pools (regular nodes + a wasi node pool), and benchmarks claim wasm images are 20–30× smaller than equivalent Linux containers while keeping native‑like speed for edge inference.
AI-written summary · about
chapters (8)
- 0:00WebAssembly for Edge AI
- 3:52Why WebAssembly for Edge
- 7:25WasmEdge Runtime on Edge
- 10:39WebAssembly + Kubernetes
- 14:14Demo: Wasm on Kubernetes
- 20:45Wasm as Serverless AI
- 22:30Running WebAssembly in Kubernetes
- 27:29Q&A on Workloads
related talks
33mWebAssembly based AI as a Service with Kubernetes
41mWebAssembly Based AI as a Service
29mSupercharge Your Kubernetes AI Deployments with Wasm
01h 04mDevelop, Build & Deploy Lightweight AI Services with WebAssembly
27mAI inference on the Edge cloud using WebAssembly
38mCloud-Native WebAssembly: Containerization On the Edge
40mWebAssembly for AI Infra : A Lightweight, Fast, and Secure Alternative Approach
33mReady, Set, Go: WASM-Powered Containers Taking Your AI To New He...