• 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
Name
Last commit
Last update
.vscode Loading commit data...
codai Loading commit data...
.gitignore Loading commit data...
LICENSE.md Loading commit data...
README.md Loading commit data...
build.sh Loading commit data...
coder Loading commit data...
coderai Loading commit data...
requirements-nvidia.txt Loading commit data...
requirements-vulkan.txt Loading commit data...
requirements.txt Loading commit data...