summaryrefslogtreecommitdiff
path: root/ggml/src/ggml.c
diff options
context:
space:
mode:
authorKawrakow <iwankawrakow@gmail.com>2024-10-01 15:52:35 +0300
committerGitHub <noreply@github.com>2024-10-01 15:52:35 +0300
commit0999f77e5b1a97164ee0218f5fc118fe1649b0a3 (patch)
treef27d4b2adab218a4e0b91a26b06ebc249a567b2c /ggml/src/ggml.c
parent970df4b46701074cf907dcbfa0cf2feab972ed0d (diff)
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>
Diffstat (limited to 'ggml/src/ggml.c')
0 files changed, 0 insertions, 0 deletions