Skip to content

Move some flashattn computation to f32 for correctness

d8d9a1e
Select commit
Loading
Failed to load commit list.
Sign in for the full log view
Merged

ggml webgpu: initial flashattention implementation #18610

Move some flashattn computation to f32 for correctness
d8d9a1e
Select commit
Loading
Failed to load commit list.
labeler
succeeded Jan 8, 2026 in 8s