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
- controller: preserve primary role-0 during scale-down
- fix(tokenizer): restore the restart budget when a renderer becomes ready
- Support cloud llm provider routing
- [Onboarding] Tracking issue for kthena moved under volcano-sh
- Handle skipped but required github action checks
- router: build a general abstraction layer for both ModelRoute/ModelServer and Gateway API/Inference Extension
- Autoscaler treats Prometheus COUNTER metrics as instantaneous values instead of cumulative
- [lfx-mentorship-2026-Sep-Nov] Kthena's LFX project declaration
- bug: DeleteModelServer does not clean up Redis on-flight counter entries for evicted pods
- Support maxUnavailable for ModelServing eviction protection
- Docs
- Go not yet supported