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
- feat(model-serving): add preStop-based lossless upgrade for ModelServing
- fix(router): drop a failed attempt's response headers before retrying
- model-serving: fix flaky controller tests
- router: fix session boost grace hold being skipped
- Enhance global rate limit of infer gateway
- Enrich the model serving status to display more information
- [Feature]: support serving groups anti-affinity
- 2026 Volcano Roadmap
- feat: Autoscaler support for PD disaggregation scaling and prefill/decode ratio adjustment
- [lfx-mentorship-2026-June-August] Kthena Router Benchmark
- Docs
- Go not yet supported