b9221
📦 llama-cppView on GitHub →
✨ 1 features🐛 2 fixes🔧 3 symbols
Summary
This release introduces support for the PAD operation on the Hexagon HTP backend via HVX kernels and resolves minor merge conflicts and configuration issues in the Hexagon implementation.
✨ New Features
- Implemented GGML_OP_PAD on the Hexagon HTP backend using HVX vectorized kernels, supporting zero-padding and circular padding across all 4 tensor dimensions.
🐛 Bug Fixes
- Removed duplicate op cases in hex-ggml (merge conflict resolution).
- Fixed editorconfig checks and macro alignment in hex-pad.