mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-01-12 19:50:17 +00:00
06658ad7c3
* metal : separate scale and mask from QKT in FA kernel * metal : ne01 check no longer necessary * metal : keep data in local memory |
||
---|---|---|
.. | ||
cmake | ||
include | ||
src | ||
.gitignore | ||
CMakeLists.txt |