COMMITS
/ core/services/nodes/router.go May 30, 2026
L
feat: prefix-cache-aware routing for distributed mode (#10071)
LocalAI [bot] committed
May 25, 2026
L
fix(distributed): persist per-model load info so reconciler survives frontend restart (#9981)
LocalAI [bot] committed
May 24, 2026
L
fix(distributed): route per request across loaded replicas + cache probeHealth (#9968)
LocalAI [bot] committed
May 23, 2026
L
fix(distributed): make admin backend installs resilient and observable (#9958)
LocalAI [bot] committed
May 8, 2026
L
fix(distributed): split NATS backend.upgrade off install + dedup loads (#9717)
LocalAI [bot] committed
May 7, 2026
L
fix(distributed): make backend upgrade actually re-install on workers (#9708)
LocalAI [bot] committed
May 6, 2026
R
feat(gallery): Speed up load times and clean gallery entries (#9211)
Richard Palethorpe committed
May 5, 2026
E
feat(concurrency-groups): per-model exclusive groups for backend loading (#9662)
Ettore Di Giacinto committed
May 4, 2026
April 27, 2026
E
feat(distributed): support multiple replicas of one model on the same node (#9583)
Ettore Di Giacinto committed
April 20, 2026
R
fix(distributed): pass ExternalURI through NATS backend install (#9446)
Russell Sim committed
April 8, 2026
E
feat: track files being staged (#9275)
Ettore Di Giacinto committed
E
fix(autoscaling): extract load model from Route() and use as well when doing autoscale (#9270)
Ettore Di Giacinto committed
March 31, 2026
E
fix(inflight): count inflight from load model, but release afterwards (#9194)
Ettore Di Giacinto committed
E
feat: add node reconciler, allow to schedule to group of nodes, min/max autoscaler (#9186)
Ettore Di Giacinto committed
March 30, 2026
E
chore(workers): improve logging, set header timeouts (#9171)
Ettore Di Giacinto committed
March 29, 2026
E
feat: add distributed mode (#9124)
Ettore Di Giacinto committed