From Event-Driven to Automotive
summary
Claims a full-stack WebAssembly pipeline that actually ships: browser ML inference with TensorFlow.js and PyTorch tooling, federated learning coordinated with PiGrid and Kubeflow, edge and cluster extensions via Wasmtime/Spin/Rust and Envoy, in-queue transformations using Redpanda-hosted Wasm modules, and an automotive wallet + smart contracts on Concordium. Teams reuse domain code across browser, edge, and Kubernetes, deploy models of about 250 MB, run a production project with a three-person team, push updates once-a-month model release, and report zero maintenance on Fastly.
AI-written summary · about
chapters (6)
- 0:00WebAssembly in automotive Edge
- 4:10Privacy-first AI in browser
- 10:33Full-stack WebAssembly analytics
- 17:40Automotive decentralized ecosystem
- 28:41Building Namio WebAssembly cloud
- 34:01Q&A model training
related talks
33mWebAssembly based AI as a Service with Kubernetes
37mAI/ML at the Extreme Edge with WebAssembly: A Path Forward
25mFrom Cloud to Edge computing - Unleashing the power of WebAssembly at the edge
01h 04mDevelop, Build & Deploy Lightweight AI Services with WebAssembly
01h 42mWebAssembly: Writing Once and Running Everywhere NG
32mWebAssembly Based AI as a Service on the Edge with Kubernetes
15mClosing Remarks
19mWebAssembly's Journey Beyond the Browser