llama.cpp icon indicating copy to clipboard operation
llama.cpp copied to clipboard
Published 2 months ago • verified publisher icon ggml-org

ggml : add missing AVX512 feature checks

Open angt opened this issue 2 months ago • 0 comments 

_mm512_cvtepu8_epi16        requires  __AVX512BW__
_mm512_srli_epi16           requires  __AVX512BW__
__builtin_ia32_inserti32x8  requires  __AVX512DQ__

angt avatar Nov 14 '25 14:11 angt