Skip to content

cuda: sliding-window attention, sigmoid top-k routing and combine, dense rows for every family, checked against float64 - #798

Closed
jschmied wants to merge 23 commits into
ashhart:mainfrom
jschmied:cuda-moe-dense-window
Closed

jschmied wants to merge 23 commits into
ashhart:mainfrom
jschmied:cuda-moe-dense-window

cuda/window_attention: the split decode and its merge move to window_…

74b749f
Select commit
Loading
Failed to load commit list.
Sign in for the full log view

Annotations

1 warning and 1 notice
zig
succeeded Oct 18, 2026 in 2m 41s