Change8

b7642

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

Summary

This release primarily addresses a build issue for AVX512BF16 support in ggml by ensuring necessary headers are included, alongside the removal of unused code.

Migration Steps

  1. If compiling with AVX512BF16 support, ensure 'immintrin.h' is included.

🐛 Bug Fixes

  • Fixed AVX512BF16 build by including 'immintrin.h' when required.

🔧 Affected Symbols

ggml