b9605
📦 llama-cppView on GitHub →
✨ 1 features🐛 1 fixes🔧 1 symbols
Summary
This release introduces support for scalar type concatenation on the CUDA backend for ggml operations and resolves a Metal CI build issue.
✨ New Features
- Added support for concatenation of scalar types on the CUDA backend within ggml.
🐛 Bug Fixes
- Fixed an issue related to the Metal CI build.