b7612
📦 llama-cppView on GitHub →
✨ 1 features🔧 1 symbols
Summary
This release focuses on internal graph optimizations by reducing topology branching. It includes a wide range of pre-built binaries for multiple operating systems and hardware accelerators including CUDA, Vulkan, and SYCL.
✨ New Features
- Optimization of graph topology branching to improve performance or memory efficiency.
🔧 Affected Symbols
graph