b9023
📦 llama-cppView on GitHub →
✨ 1 features🔧 1 symbols
Summary
This release introduces a new server endpoint, /models?reload=1, and provides updated pre-compiled binaries for macOS, Linux, Android, Windows, and openEuler supporting various CPU, GPU (Vulkan, ROCm, SYCL, HIP, CUDA), and specialized hardware configurations.
✨ New Features
- Implemented a new server endpoint: /models?reload=1.