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
- [netlify][docs] no changes detected
- Should prevent updating Gangpolicy and NetworkTopology?
- [Feat] Design and implement status fields of ModelRoute & ModelServer
- Propsal：Fine-Grained Instance Health Check for Kthena Router
- feat: Cost-aware request queuing in kthena-router to prevent backend LLM engine overloading
- bug: ParsePrompt silently drops chat messages with array content, causing 0 input-token accounting and empty prefix-cache keys
- [FE] [Benchmark] Add pprof analysis module in benchmark suite
- router: reject cross-namespace HTTPRoute backends
- perf: compile HTTPRoute regex path matchers once
- Support core HTTPRoute request header and redirect filters
- Docs
- Go not yet supported