mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-02-09 09:48:16 +01:00
![]() * separate DPCT helpers outside * replace global variables with context * remove useless extra * update mul_mat condition * remove duplicate buft initialization * remove duplicate extra and global work group size * remove useless backend check * remove duplicated extras * use macro for group_size and remove cuda-related |
||
---|---|---|
.. | ||
helper.hpp |