Release Notes for the KubeEdge Edge Service blueprint.

Summary

KubeEdge Edge Service is a blueprint family which showcases end-to-end solution for edge services with KubeEdge centered edge stack. The first release will focus on the ML inference offloading use case.

KubeEdge is a CNCF sandbox project widely adopted as a key industry reference Edge Computing architecture. With KubeEdge, application vendors can push a wide range of applications at the edge, including Mobile Edge services. It is an upstream project to Akraino community. There are other Akraino Blueprint projects with KubeEdge incorporated. This project family will focus on solutions centered around KubeEdge. Future releases may incorporate various components, e.g. hardware infrastructure etc.

What is released

Components of the release

Machine learning offloading core services.
Model controller is for managing the life cycles of the machine learning models, including model creation, update, deployment and deletion. It leverages the declarative API of K8s CRD and orchestrate the cloud-edge collaboration.
Dataset controller is for managing the machine learning datasets. It leverages Kubernetes CRD in a similar way as the model controller.

Dependencies of the release

Upstream projects :

- KubeEdge version 1.4

- Kubernetes version 1.19

Release Data

Software Deliverable

https://github.com/kubeedge/kubeedge

https://github.com/futurewei-cloud/kubeedge-android-ai

Documentation Deliverable

Known Limitations, Issues and Workarounds

N/A

Browser not supported