b9490
📦 llama-cppView on GitHub →
✨ 1 features🔧 1 symbols
Summary
This release updates ggml-cpu to use the runtime SVE width in FWHT calculations. It also provides numerous pre-built binaries for various operating systems and hardware configurations, while disabling several specific build targets.
✨ New Features
- ggml-cpu: use runtime SVE width in FWHT