• Your Name's avatar
    Fix: Proper model resolution for ondemand mode - unload when switching between ANY different models · a37085b4
    Your Name authored
    - Added resolve_model_name() to MultiModelManager to properly resolve model aliases
    - Added get_currently_loaded_model_name() to track what's actually in VRAM
    - Updated /v1/chat/completions, /v1/completions, and /v1/images/generations
    - Now correctly compares resolved canonical names before deciding to unload
    - Handles all aliases (default, image, audio, tts) and custom aliases
    - Works across ALL model types: text->text2, image->image2, text->image, etc.
    a37085b4
text.py 86.4 KB