-
v0.9.9-rc3
Pre-releaseAll checks were successfulBuild and Publish Docker Image (Semantic Cache) / build (amd64, linux/amd64, docker-amd64) (push) Successful in 3m59sBuild and Publish Docker Image / build (amd64, linux/amd64, docker-amd64) (push) Successful in 1m25sBuild and Publish Docker Image / build (arm64, linux/arm64, docker-arm64) (push) Successful in 12m46sBuild and Publish Docker Image / merge (push) Successful in 33sBuild and Publish Docker Image (Semantic Cache) / build (arm64, linux/arm64, docker-arm64) (push) Successful in 19m56sBuild and Publish Docker Image (Semantic Cache) / merge (push) Successful in 33sreleased this
2026-06-07 10:00:56 +02:00 | 1 commits to dev-0.9.x-ref since this release- refactor of nomyo-router for better maintainability
- support llama-server authorization headers
- improved endpoint check locks and seperate connection pool to improve stability in high load situations
- making ollama backend errors transient to surface backend errors to clients for better debugging
- automatic SSE reconnect on dashboard to prevent API Key modal blips
- adding load test to judge machine performance
- cache http-clients to prevent full init with CA OS trust store for any request causing a massive performance ceiling
pre-release for testing
don't use in production -
v0.9.1
StableAll checks were successfulBuild and Publish Docker Image (Semantic Cache) / build (amd64, linux/amd64, docker-amd64) (push) Successful in 3m35sBuild and Publish Docker Image / build (amd64, linux/amd64, docker-amd64) (push) Successful in 1m18sBuild and Publish Docker Image (Semantic Cache) / build (arm64, linux/arm64, docker-arm64) (push) Successful in 14m28sBuild and Publish Docker Image (Semantic Cache) / merge (push) Successful in 33sBuild and Publish Docker Image / build (arm64, linux/arm64, docker-arm64) (push) Successful in 11m28sBuild and Publish Docker Image / merge (push) Successful in 33sreleased this
2026-05-19 07:11:46 +02:00 | 10 commits to main since this release- fix health endpoint for ollama endpoints
- fix docker image build
- doc update
-
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
-
v0.8.1
StableSome checks failedBuild and Publish Docker Image (Semantic Cache) / build (arm64, linux/arm64, docker-arm64) (push) Successful in 10m41sBuild and Publish Docker Image (Semantic Cache) / build (amd64, linux/amd64, docker-amd64) (push) Successful in 35sBuild and Publish Docker Image (Semantic Cache) / merge (push) Successful in 32sBuild and Publish Docker Image / merge (push) Has been skippedBuild and Publish Docker Image / build (arm64, linux/arm64, docker-arm64) (push) Successful in 10m40sBuild and Publish Docker Image / build (amd64, linux/amd64, docker-amd64) (push) Failing after 1m20sreleased this
2026-05-11 09:52:28 +02:00 | 50 commits to main since this release- updated docs
- feat: new helper to bridge change of behaviour in llama.cpp v1/models status
- feat: better default referer handling when requesting remote endpoints
- feat: correct pass through of openai.APIStatusErrors to be able to debug client-side
-
v0.8.0
StableAll checks were successfulBuild and Publish Docker Image (Semantic Cache) / build (amd64, linux/amd64, docker-amd64) (push) Successful in 38sBuild and Publish Docker Image / build (amd64, linux/amd64, docker-amd64) (push) Successful in 37sBuild and Publish Docker Image (Semantic Cache) / build (arm64, linux/arm64, docker-arm64) (push) Successful in 9m57sBuild and Publish Docker Image (Semantic Cache) / merge (push) Successful in 34sBuild and Publish Docker Image / build (arm64, linux/arm64, docker-arm64) (push) Successful in 10m32sBuild and Publish Docker Image / merge (push) Successful in 32sreleased this
2026-05-01 16:58:27 +02:00 | 115 commits to main since this releasenew features:
- priority routing
- endpoint specific max_connection settings
- updated docs
- direct llama_server_endpoint connection via unix socket bypassing network overhead
-
v0.7.6
StableAll checks were successfulBuild and Publish Docker Image (Semantic Cache) / build (amd64, linux/amd64, docker-amd64) (push) Successful in 34sBuild and Publish Docker Image / build (amd64, linux/amd64, docker-amd64) (push) Successful in 38sBuild and Publish Docker Image (Semantic Cache) / build (arm64, linux/arm64, docker-arm64) (push) Successful in 10m5sBuild and Publish Docker Image (Semantic Cache) / merge (push) Successful in 31sBuild and Publish Docker Image / build (arm64, linux/arm64, docker-arm64) (push) Successful in 10m11sBuild and Publish Docker Image / merge (push) Successful in 31sreleased this
2026-04-16 13:29:27 +02:00 | 124 commits to main since this release- fixing a bug in /health endpoint
- mitigating a possible dependency vulnerability
- improved documentation on the reactive context-shift feature
-
v0.7.5
StableAll checks were successfulBuild and Publish Docker Image (Semantic Cache) / build (amd64, linux/amd64, docker-amd64) (push) Successful in 37sBuild and Publish Docker Image / build (amd64, linux/amd64, docker-amd64) (push) Successful in 36sBuild and Publish Docker Image (Semantic Cache) / build (arm64, linux/arm64, docker-arm64) (push) Successful in 10m10sBuild and Publish Docker Image (Semantic Cache) / merge (push) Successful in 33sBuild and Publish Docker Image / build (arm64, linux/arm64, docker-arm64) (push) Successful in 10m2sBuild and Publish Docker Image / merge (push) Successful in 33sreleased this
2026-04-13 15:19:22 +02:00 | 129 commits to main since this release- dashboard security fix
- dashboard hostname inclusion improving host visibility when managing multiple instances
-
v0.7.4
StableAll checks were successfulBuild and Publish Docker Image (Semantic Cache) / build (amd64, linux/amd64, docker-amd64) (push) Successful in 35sBuild and Publish Docker Image / build (amd64, linux/amd64, docker-amd64) (push) Successful in 36sBuild and Publish Docker Image (Semantic Cache) / build (arm64, linux/arm64, docker-arm64) (push) Successful in 10m21sBuild and Publish Docker Image (Semantic Cache) / merge (push) Successful in 32sBuild and Publish Docker Image / build (arm64, linux/arm64, docker-arm64) (push) Successful in 10m3sBuild and Publish Docker Image / merge (push) Successful in 32sreleased this
2026-04-08 18:02:27 +02:00 | 132 commits to main since this releasehot-fix release fixing ollama /api/chat
-
v0.7.3
StableAll checks were successfulBuild and Publish Docker Image (Semantic Cache) / build (amd64, linux/amd64, docker-amd64) (push) Successful in 37sBuild and Publish Docker Image / build (amd64, linux/amd64, docker-amd64) (push) Successful in 35sBuild and Publish Docker Image (Semantic Cache) / build (arm64, linux/arm64, docker-arm64) (push) Successful in 10m8sBuild and Publish Docker Image (Semantic Cache) / merge (push) Successful in 34sBuild and Publish Docker Image / build (arm64, linux/arm64, docker-arm64) (push) Successful in 10m4sBuild and Publish Docker Image / merge (push) Successful in 34sreleased this
2026-04-07 17:16:54 +02:00 | 143 commits to main since this releasefinal v0.7 service release with performance related improvements and fixes
-
v0.7.2
Stablereleased this
2026-04-02 09:19:36 +02:00 | 190 commits to main since this releasenew dashboard TPS graph