Kawrakow 472b4c37c1 Option to use MLA without a transposed cache (#235) ...

The `-mla` command line option turns into an int from a bool.
mla = 0: use standard attention
mla = 1: use MLA with transposed cache
mla > 1: use MLA without transposed cache

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

2025-02-27 16:40:49 +02:00

20 KiB

Raw Blame History

View Raw