KubeEdge Powered Edge-Devices With Next Generation Cloud Native Runtime
Talkat KubeCon + CloudNativeCon + Open Source Summit China 2021 · on Friday, 2021-12-10· at 14:05· Kubecon + CloudNativeCon 演讲厅, 虚拟会议 (Virtual)·
summary
Explains the need for a lightweight, cross-architecture cloud-native runtime for edge devices using KubeEdge to enable edge–cloud collaboration. Covers challenges from diverse chips, hardware accelerators and tinyML on resource-constrained devices, and argues for a unified container sandbox approach that provides low overhead, fast startup and isolation to simplify multi-architecture migration and reduce development/maintenance costs.
AI-written summary · about
chapters (18)
- 0:00Intro
- 0:29About Me
- 1:16Agenda
- 1:34Motivation
- 3:46Design Goal
- 4:43KubeEdge Overview
- 5:54iSula Overview
- 7:05WebAssembly & WASI
- 8:29WebAssembly Performance
- 9:16WebAssembly Replace Docker? O
- 10:47Docker vs WebAssembly
- 12:52WebAssembly Runtimes
- 13:14Write another WASM runtime?
- 14:35Krustlet
- 15:38WasmEngine Arch
- 18:05WasmEngine Scheduler DesigA E
- 18:32WasmEngine Scheduler Design
- 19:53Future Work
related talks
25mManage Cloud Native LLM Workloads Across Edge and Cloud Seamlessly Using KubeEdge and WasmEdge
38mCloud-Native WebAssembly: Containerization On the Edge
48mExtending Cloud Native Beyond the “Linux Barrier” to MCUs
12mLightning Talk: Orchestrating Machine Learning on Edge Devices...
48mExtending Cloud Native Beyond the “Linux Barrier” to MCUs
31mWith WasmEdge to New Shores
25mFrom Cloud to Edge computing - Unleashing the power of WebAssembly at the edge
13mKeynote: WEdge Project: Edge AI enabled by Wasm