b8761
📦 llama-cppView on GitHub →
✨ 3 features🐛 1 fixes🔧 1 symbols
Summary
This release introduces basic support for the q5_k quantization format on OpenCL, including necessary matrix operation implementations and associated unit test fixes. It also provides a wide array of pre-compiled binaries for diverse operating systems and hardware accelerators.
✨ New Features
- Added basic support for q5_k quantization format on OpenCL.
- Added general q5_k matrix-vector (mv) operation support for OpenCL.
- Added flattened Q5_K matrix-matrix (mm) and general Q5_K mv support for OpenCL.
🐛 Bug Fixes
- Fixed Q5_K unit tests related to OpenCL implementation.