webgpu: fix OOB subgroup-matrix loads for trailing partial tiles #32364
qjia7
commented
on 2026-09-06
qjia7
commented
on 2026-09-06
webgpu: fix out-of-bounds subgroup-matrix loads for trailing partial …
dab4e364
jchen10
force pushed
from
118c0b4a
to
dab4e364
52 days ago
Split odd-N B padding into N_b computation and dispatch steps
f6232ddc
qjia7
approved these changes
on 2026-09-07
jchen10
deleted the sgmm_robust branch 15 days ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub