b10712
📦 llama-cppView on GitHub →
✨ 3 features🔧 1 symbols
Summary
This release introduces Vulkan backend improvements for top-k operations with Qwen 3.8 Flash Next, including a new radix sort shader and qsa fusion. It also includes updated test cases for this functionality.
✨ New Features
- Added top-k radix sort shader for k >= 1024 in Vulkan backend.
- Integrated Qwen 3.8 Flash Next top-k tests.
- Implemented top-k qsa fusion.