b8108
📦 llama-cppView on GitHub →
🐛 2 fixes🔧 1 symbols
Summary
This release addresses a critical bug in Qwen3.5 model shapes and optimizes continuous operations by removing unnecessary reshapes. It also provides updated binaries for numerous platforms.
🐛 Bug Fixes
- Fixed incorrect beta/gate shapes for qwen3.5 models.
- Avoided extra reshapes in continuous operations.