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
- model-serving: keep CurrentRevision until the target is ready
- Improve router request priority calculation beyond simple token count
- fix: reject empty parent in serving group names
- Proposal: Handle configuration drift when updating ModelServing scheduling fields (gangPolicy/networkTopology)
- fix: validate modelroute target entries and guard nil targets
- controller: retry AutoscalingPolicy and LeaderWorkerSet status updates on conflict
- runtime: vLLM KV-event decoder expects legacy array-shaped events
- test: move Redis e2e fixture into utils
- test/e2e: check helm in the e2e preflight
- bug(router): model discovery fails when the backend enables API-key auth (GET /v1/models is intercepted with 401)
- Docs
- Go not yet supported