Change8

b8412

📦 llama-cppView on GitHub →
🐛 1 fixes🔧 1 symbols

Summary

This release addresses a minor warning in the x86 CPU backend and provides updated binary distributions for macOS, Linux, Windows, and openEuler supporting various hardware accelerators like ROCm, Vulkan, and CUDA.

🐛 Bug Fixes

  • Fixed an unused changemask warning in ggml-cpu/x86 repack operations (#20692).

Affected Symbols