b10509
📦 llama-cppView on GitHub →
✨ 1 features🔧 1 symbols
Summary
Introduced `ggml_rope_set_offset` with expanded backend support including Metal, CUDA, and Vulkan. This release also provides updated pre-compiled binaries for various platforms and hardware configurations.
✨ New Features
- Added `ggml_rope_set_offset` function with support for Metal, CUDA, and Vulkan backends.