b8742
📦 llama-cppView on GitHub →
✨ 2 features🔧 2 symbols
Summary
This release introduces support for Q1_0 quantization format within the Vulkan backend and updates internal dependency usage by incorporating 'get_dm'.
✨ New Features
- Vulkan backend now supports Q1_0 quantization format.
- Introduced usage of 'get_dm' function.