mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-01-12 13:27:21 +01:00
a91a41364b
Change the code to do 16b loads when possible and extract the appropriate component late, so the code is effectively decoding a pair of elements and then selecting one. This can allow more commoning to happen in the compiler when neighboring elements are loaded.