Kawrakow d2c74a369b Fix Q5_0 flash attention (#75) ...

When I changed iqk_mul_mat to use type-1 dot products for type-0
legacy quants, I forgot to also change the vec_dot_type when
the dot product is done via ggml as in flash attention.
This commit fixes it.

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

2024-10-01 15:52:35 +03:00

..

cmake

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

include

Adding SWIGLU unary op (#65)

2024-09-28 13:37:25 +03:00

src

Fix Q5_0 flash attention (#75)

2024-10-01 15:52:35 +03:00

.gitignore

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

CMakeLists.txt

Merge mainline - Aug 12 2024 (#17)

2024-08-12 15:14:32 +02:00