main
Cleanup plugins docs (#3396)
Fixes for worker prompt truncation in ChatML case (#3673)
Support ChatML prompt format in worker (#3668)
Introduce model configs to abstract pairings of models and hardware (#2194)
changed basic hf server to support quantization and streaming (#2293)
Initial inference documentation pass (#3330)
Basic implementation of an plugin system for OA (#2765)
fix for plugins openapi parser (#3316)
Fixed worker requirements wrt transformers (#2621)
Fix plugins (#3017)
Improvements to the HF worker container (#2339)
Added docker image for standalone worker (#2300)