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
- test: cover KV-cache prefix matching and removal
- Proposal for kthena router benchmark (Python version)
- fix(model-serving): guard empty OwnerReferences in role reconciliation
- improve LeaderWorkerSet runtime and status compatibility
- router: keep rate limiter state when ModelRoute config is unchanged
- docs: add ecosystem volcano
- fix unstable e2e test about modelserving partition
- workload: validate plugin scope target
- controller: read latest object from API server before status retry
- datastore: clean up Redis on-flight counter when pod is evicted in DeleteModelServer
- Docs
- Go not yet supported