Change8

b8175

📦 llama-cppView on GitHub →
1 features🔧 1 symbols

Summary

This release introduces repack support for mxfp4 quantization within ggml-cpu and provides updated pre-compiled binaries across various operating systems and hardware configurations.

✨ New Features

  • Added repack functionality for mxfp4 quantization in ggml-cpu.

Affected Symbols