b9741
📦 llama-cppView on GitHub →
✨ 1 features🔧 1 symbols
Summary
The llama component has been updated to utilize LLM_KV for setting quantization_version and file_type. Numerous pre-compiled binaries for different operating systems and hardware configurations are provided.
✨ New Features
- Quantization version and file type are now read from LLM_KV for llama models.