Skip to content

v1.0.14 – llama-cpp-python MTMD Compatibility Fix

Latest

Choose a tag to compare

@kantan-kanto kantan-kanto released this 16 Jun 10:57

Fixed local Qwen GGUF vision handler initialization with recent JamePeng llama-cpp-python builds

Added runtime compatibility for MTMD handlers that expect mmproj_path
Preserved compatibility with older builds that still require clip_model_path
Prevented Qwen3-VL and Qwen3.5/3.6 local vision runs from falling back to text-only mode because of the handler keyword mismatch

Improved mmproj logging for local Qwen vision models

Reports the selected mmproj after manual selection or auto-detection
Avoids printing Using mmproj: None for text-only paths