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
- autoscaler: honor PrometheusMetricSource.auth for bearer token and TLS
- fix(router): keep same-user FIFO when priority refresh is enabled
- feat: support per-pod ports for host-network workloads
- bug(router): input token quota consumed on failed requests when pod discovery returns no backend
- 📢 Call for Community: Reviewers and Technical Leaders Wanted!
- router: fix lora-only route rate limits
- During a rolling update, maintain a certain ratio among the different roles
- router: fix prefix cache races with pod deletion
- fix(router): reject malformed chat messages instead of silently dropping them
- router: ignore runtime sidecar restarts in kvcache freshness
- Docs
- Go not yet supported