b9041
📦 llama-cppView on GitHub →
✨ 1 features🔧 1 symbols
Summary
This release introduces a performance optimization by fusing RMS_NORM and MUL operations on the CPU backend. It also provides extensive pre-compiled binaries for macOS, Linux, Android, Windows, and openEuler platforms.
✨ New Features
- Fused RMS_NORM + MUL operation optimization on the CPU backend.