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
- cleanup(router): make HTTPConnector and NIXLConnector stateless
- fix(autoscaler): weight heterogeneous metrics by replicas
- Is a global maxWaitingRequests threshold suitable for ModelServers with different capacities?
- feat(router): support Host-based modelMatch and pass through backend 4xx
- test(e2e): add tokenizer service tests for sidecar and standalone modes
- [Docs] Documentation Improvements
- feat(model-serving): support role-scoped network topology policies
- [lfx-mentorship-2026-Sep-Nov] Build a KVCache-aware scheduler E2E test suite
- model-serving-controller: guard OwnerReferences index in role reconcilation
- router: add SchedulerProfile CRD for per-ModelServer scheduler configuration
- Docs
- Go not yet supported