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
- Keep regular replicas separate from temporary rollout replicas
- Keep the last completed revision until the rollout is Ready
- Explain ModelServing rollout, scaling and recovery behavior
- router: update Gateway API status conditions for GatewayClass, Gateway, and HTTPRoute
- model-serving: detect failed rollouts and optionally roll back
- Tokenizer service abandons a model once its lifetime restart count reaches RENDERER_MAX_RESTARTS
- cli: DeepSeek-R1-Distill-Qwen-32B template renders invalid YAML, so kthena create manifest fails
- cli: fix the config indentation in the DeepSeek-R1-Distill-Qwen-32B template
- feat(router): support Redis authentication for session-sticky storage
- controller-manager: skip the ModelBooster controller without the networking CRDs
- Docs
- Go not yet supported