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
- bug: jwk.Fetch uses context.Background() with no timeout — blocks router startup on slow JWKS server
- test: Controller-manager E2E tests are flaky due to external model/image dependencies
- AutoscalingPolicy and LeaderWorkerSet status updates don't retry on conflict (409)
- test: wait for generated ModelBooster Pods to terminate before subsequent E2E tests
- perf: tiktoken BPE encoding re-initialized on every call in TickToken
- perf: GlobalRateLimiter writes Redis state on denied requests and read-only Tokens() calls
- bug: AutoscaleController omits status, conditions, and observedGeneration updates for HomogeneousTarget and HeterogeneousTarget policies
- feat(router): honor weighted HTTPRoute InferencePool backendRefs
- feat(router): support HTTPRoute method, header, and query parameter matching
- reliability(router): bound HTTP headers and inference request body size
- Docs
- Go not yet supported