b9473
📦 llama-cppView on GitHub →
✨ 1 features🔧 1 symbols
Summary
This release focuses on an optimization for the KV cache in SWA checkpoints, storing only non-masked cells. It also provides numerous pre-compiled binaries for various operating systems and hardware configurations.
✨ New Features
- KV cache now stores only non-masked cells in SWA checkpoints.