feat(cluster,api,models,cli): add cluster-aware model catalog deployments and request routing
This commit is contained in:
@@ -1,5 +1,14 @@
|
||||
# Changelog
|
||||
|
||||
## 2026-04-20 - 1.1.0 - feat(cluster,api,models,cli)
|
||||
add cluster-aware model catalog deployments and request routing
|
||||
|
||||
- introduces cluster management, placement, heartbeats, desired replica reconciliation, and internal /_cluster control-plane endpoints
|
||||
- switches model discovery from a greenlist to a public catalog with canonical model resolution and registry-backed validation
|
||||
- routes chat and embeddings requests to local or remote nodes based on cluster placement and exposes cluster-aware model listings
|
||||
- adds CLI commands for cluster operations plus simplified run/ps deployment workflows focused on vLLM
|
||||
- removes Ollama container support and reorients configuration, defaults, and docs around catalog-backed vLLM deployments
|
||||
|
||||
## 2026-01-30 - 1.0.1 - fix(docs)
|
||||
revamp README with updated branding, expanded features, installation and uninstall instructions, resources, and legal/company information
|
||||
|
||||
|
||||
Reference in New Issue
Block a user