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
- controller: exit process on leader election loss
- Support protobuf coding in kubeclient
- User/Group based token ratelimit
- bug: TokenRateLimiter reuses first model's Redis client for all subsequent models
- What are the minimum inference-engine / connector version requirements for PD disaggregation?
- bug: AutoscaleController reconcile loop does not stop on controller context cancellation
- bug: Python S3/PVC downloaders deadlock when subprocess stderr fills OS pipe buffer
- ServingGroup status is not downgraded during RoleRollingUpdate, causing inflated availableReplicas
- Synchronous sleep in waitGraceAndDequeue blocks entire SessionBoost dispatch loop
- feat(cleanup/refactor): add unit tests for calMaxScaleDown function and refactor its implementation
- Docs
- Go not yet supported