mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-03-03 18:40:14 +00:00
* Remove iqk_mul_mat from llamafile_sgemm * Pass tensor types and strides to iqk_mul_mat It is marked WIP because only tested on __aarch64__
31 KiB
31 KiB