ggml : fix unnecessary f32 -> f16 -> f32 casts (mmla) #5951
ggml : fix unnecessary f32 -> f16 -> f32 casts (mmla)
9914a71e
ggerganov
merged
8380ecfb
into master 2 years ago
ggerganov
deleted the gg/fix-mmla-q4_1-q8_1 branch 2 years ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub