b9932
📦 llama-cppView on GitHub →
✨ 1 features🐛 1 fixes🔧 1 symbols
Summary
This release focuses on performance tuning for the Vulkan backend by disabling FA mask_opt on GCN, while re-enabling mask optimization for attention head size 256.
✨ New Features
- Reenabled mask optimization over attention head size 256.
🐛 Bug Fixes
- Disabled FA mask_opt on GCN (Vulkan backend) to improve performance.