Skip to content

Fix LGA cache devices and skipped-attention residuals (#22087) - #22087

Open
YIWENX14 wants to merge 1 commit into
pytorch:mainfrom
YIWENX14:export-D117006258
Open

Fix LGA cache devices and skipped-attention residuals (#22087)#22087
YIWENX14 wants to merge 1 commit into
pytorch:mainfrom
YIWENX14:export-D117006258

Conversation

@YIWENX14

@YIWENX14 YIWENX14 commented Aug 24, 2026 •
edited by meta-codesync Bot
Loading

Copy link
Copy Markdown
Contributor

Summary:

Make KV-cache indices and sliding-window masks follow the cache device so LGA eager execution works on CUDA. Match RLFormers semantics for attention-skip layers by applying the gated residual to a zero attention branch.

Reviewed By: billmguo

Differential Revision: D117006258

@pytorch-bot

pytorch-bot Bot commented Aug 24, 2026 •
edited
Loading

Copy link
Copy Markdown

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/22087

Note: Links to docs will display an error until the docs builds have been completed.

✅ No Failures

As of commit 0b61348 with merge base 9a2d135 (image):
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@meta-cla meta-cla Bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Aug 24, 2026
@meta-codesync

meta-codesync Bot commented Aug 24, 2026

Copy link
Copy Markdown
Contributor

@YIWENX14 has exported this pull request. If you are a Meta employee, you can view the originating Diff in D117006258.

@github-actions

github-actions Bot commented Aug 24, 2026

Copy link
Copy Markdown

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

@YIWENX14
YIWENX14 requested a review from billmguo August 24, 2026 16:54
billmguo
billmguo approved these changes Aug 24, 2026
View reviewed changes

@billmguo billmguo left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

fix the lint issue

@YIWENX14 @facebook-github-bot
Fix LGA cache devices and skipped-attention residuals (pytorch#22087)
0b61348 
Summary:

Make KV-cache indices and sliding-window masks follow the cache device so LGA eager execution works on CUDA. Match RLFormers semantics for attention-skip layers by applying the gated residual to a zero attention branch.

Reviewed By: billmguo

Differential Revision: D117006258
@meta-codesync meta-codesync Bot changed the title Fix LGA cache devices and skipped-attention residuals Fix LGA cache devices and skipped-attention residuals (#22087) Aug 24, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@billmguo billmguo billmguo approved these changes

Assignees

No one assigned

Labels

CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. meta-exported

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@YIWENX14 @billmguo