kthena
https://github.com/volcano-sh/kthena
Go
Lightweight, Modular, Kubernetes-native AI serving platform for scalable model serving.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Go not yet supported1 Subscribers
Add a CodeTriage badge to kthena
Help out
- Issues
- Add ExternalProvider support to ModelServerSpec for external cloud LLM routing
- Autoscaler is purely reactive — scale-up lags behind traffic peaks for GB-scale model images
- feat(router): support HTTPRoute header and redirect filters
- router: read every engine's vLLM metrics series
- Gang scheduling breaks with DRA ResourceClaims: aggregateResources ignores resourceClaims, leaving PodGroup minResources empty
- E2E: Add e2e tests for autoscaling using the dynamo mocker
- benchmark: integrate pprof analysis into reports
- autoscaler: populate status, conditions, and observedGeneration for homogeneous and heterogeneous policies
- fix(model-serving): prevent panic when pod has no owner references
- router: make the kvcache GC configurable and stoppable
- Docs
- Go not yet supported