●Change8

b7662

Breaking Changes
📦 llama-cppView on GitHub →
⚠ 1 breaking✨ 1 features🔧 1 symbols

Summary

This release removes the 'llama-run' tool and provides updated pre-compiled binaries for a wide range of operating systems and hardware configurations, including new CUDA 13.1 support for Windows.

⚠️ Breaking Changes

  • The 'llama-run' tool has been removed from the repository, which may break scripts or workflows relying on it.

Migration Steps

  1. If you were using 'llama-run', you must find an alternative tool or script to achieve the same functionality.

✨ New Features

  • New pre-compiled binaries provided for various platforms including macOS (Apple Silicon/Intel), Linux (Ubuntu CPU/Vulkan), Windows (CPU/CUDA 12.4/13.1/Vulkan/SYCL/HIP), and openEuler.

🔧 Affected Symbols

llama-run