v0.0.3-alpha29
Inference worker inform backend on safety intervention (#2505)
Plugins intermediate steps reporting (#3238)
Introduce model configs to abstract pairings of models and hardware (#2194)
Added max messages and max message length settings for inference (#2774)
adjusted token buffer to pop EOS
Add inference api docs (#3059)
revert postgres port in `full-dev-setup` (#3022)