Change8

b9721

📦 llama-cppView on GitHub →
3 features

Summary

This release synchronizes with ggml and provides a comprehensive set of pre-built binaries across various operating systems and hardware accelerators.

Migration Steps

  1. For macOS Apple Silicon builds, note that KleidiAI support has been explicitly DISABLED.

✨ New Features

  • Updated synchronization mechanism to ggml.
  • Provided pre-built binaries for macOS (Apple Silicon and Intel), Linux (various architectures and backends like Vulkan, ROCm 7.2, OpenVINO, SYCL), Android, and Windows (CPU, CUDA 12.4/13.3, Vulkan, OpenVINO, SYCL, HIP).
  • Released a dedicated UI binary.