Skip to content

[Bugfix] typo fix in NPU FA #12129

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Aug 12, 2025
Merged

[Bugfix] typo fix in NPU FA #12129

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b46b20a
[Bugfix] typo error in npu FA
Aug 12, 2025
b1f7bee
Merge branch 'main' into npu
a-r-r-o-w Aug 12, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion src/diffusers/models/attention_dispatch.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -944,7 +944,7 @@ def _native_npu_attention(
pse=None,
scale=1.0 / math.sqrt(query.shape[-1]) if scale is None else scale,
pre_tockens=65536,
next_tokens=65536,
next_tockens=65536,
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

tockens is a wrong spelling no?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

In npu_fusion_attention, it has to be tockens in pre_tockens and next_tockens

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please refer to

diffusers/src/diffusers/models/attention_processor.py

Line 3212 in a2ed6b4

next_tockens=65536,

keep_prob=1.0 - dropout_p,
sync=False,
inner_precise=0,
Expand Down