-
v0.9.0
StableAll checks were successfulBuild and Publish Docker Image (Semantic Cache) / build (amd64, linux/amd64, docker-amd64) (push) Successful in 3m11sBuild and Publish Docker Image / build (amd64, linux/amd64, docker-amd64) (push) Successful in 1m21sBuild and Publish Docker Image (Semantic Cache) / build (arm64, linux/arm64, docker-arm64) (push) Successful in 14m46sBuild and Publish Docker Image (Semantic Cache) / merge (push) Successful in 35sBuild and Publish Docker Image / build (arm64, linux/arm64, docker-arm64) (push) Successful in 11m58sBuild and Publish Docker Image / merge (push) Successful in 35sreleased this
2026-05-15 16:05:55 +02:00 | 23 commits to main since this release- updated docs
- fix: shutdown tasks for clean stop
- new feature: conversation affinity causes conversation stickyness to a given endpoint to leverage hot kv-caches (dramatically lowers response latency with larger context sizes)
- new feature: visualization of conversation affinity in the dashboard
- dead code removal
- CI improvements