v0.0.3-alpha25
Inference worker inform backend on safety intervention (#2505)
Basic implementation of an plugin system for OA (#2765)
Introduce model configs to abstract pairings of models and hardware (#2194)
Added max messages and max message length settings for inference (#2774)
Fix plugins (#3017)
adjusted token buffer to pop EOS
update inference readme (#2969)
revert postgres port in `full-dev-setup` (#3022)