Change8

b9169

📦 llama-cppView on GitHub →
2 features🐛 3 fixes🔧 1 symbols

Summary

This release introduces chunking support and preprocessing fixes for the qwen3a model within mtmd, alongside several minor internal adjustments and the distribution of new binaries for various platforms.

✨ New Features

  • Added support for chunks in mtmd processing.
  • Implemented preprocessing fixes for qwen3a model.

🐛 Bug Fixes

  • Corrected audio tokens.
  • Re-ordered the set_input case.
  • Removed unnecessary attn_mask usage after initial addition.

Affected Symbols