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
- Fix disaggregated autoscaler ratio constraint rounding
- Proposal: Support In-Place Rolling Update
- Proposal: Support Configurable Orchestration of Inference Pipeline
- feat: set SG unavailable while role is rolling
- refactor(router): migrate llm response parsing to official openai-go sdk
- fix(autoscaler): validate replica range for all target types
- docs(proposal): add lossless upgrade proposal for ModelServing
- Problems setting Model Router for a multi-node deployment
- Support OpenAI-compatible Batch API (/v1/batches and /v1/files)
- fix(router): defer quota until backend discovery
- Docs
- Go not yet supported