[webgpu] Fix multihead-attention for ort-web-tests #24485
qjia7
commented
on 2025-04-21
[webgpu] Fix multihead-attention for ort-web-tests
e42e741e
Compute total_sequence_length conditionally for GQA
aa0e089f
jchen10
force pushed
from
e6df1c88
to
aa0e089f
1 year ago
fs-eire
approved these changes
on 2025-04-29
fs-eire
merged
45134763
into main 1 year ago
jchen10
deleted the mha branch 1 year ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub