Connecting to devices at the edge with minimal footprint using AKS Edge Essentials and Akri on WASMs
summary
Claims running AKS Edge Essentials on devices with as little as 4GB RAM and 2vCPU and running Akri as a WASM makes the OCI image 54 times smaller. Demo connects an RTSP camera via Akri, deploys a Slight WASM that runs an ONNX model and returns bounding boxes labels and confidence, and shows the service reachable from the host and Azure Arc. It works end to end but surfaces issues: containerd/logging rough edges and was-cnn Onyx inference integration still causes friction.
AI-written summary · about
chapters (6)
- 0:00Start
- 1:03What's the Edge?
- 2:42Edge is really complex
- 5:42AKS Edge Essentials Technology Stack
- 6:48WASMs help address main edge problems
- 17:20Next steps
related talks
25mOrchestrating Machine Learning on Edge Devices Using Akri and WebAssembly
29mLiving on the Edge: Using IoT Devices on Kubernetes WebAssembly Applications
24mFrom Sensors to Servers: Efficient Edge Computing with Akri and WebAssembly
32mWebAssembly Based AI as a Service on the Edge with Kubernetes
12mLightning Talk: Orchestrating Machine Learning on Edge Devices...
07mLightning Talk: AI at the Edge: ONNX Inference in WASM on Featherweight K0s
33mReady, Set, Go: WASM-Powered Containers Taking Your AI To New He...
33mWebAssembly based AI as a Service with Kubernetes