b9831
📦 llama-cppView on GitHub →
✨ 2 features🔧 2 symbols
Summary
This release introduces DFlash v2 support, including sliding window attention configuration, and provides updated pre-compiled binaries for numerous platforms and hardware accelerators.
✨ New Features
- Added support for DFlash v2 specification.
- Implemented support for sliding window attention per layer_types in dflash.