ggml-webgpu: tune subgroup split (d_split) in flash_attn_vec #25418
add tuning params of d_split in fa
0f45c1a7
yomaytk
requested a review
2 days ago
yomaytk
merged
32e41fa5
into master 1 day ago
yomaytk
deleted the improve-fa branch 1 day ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub