-
Notifications
You must be signed in to change notification settings - Fork 713
Fix static attention non-HF RoPE implementation #11808
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.
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
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11808
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 992803c with merge base a1dec07 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
This pull request was exported from Phabricator. Differential Revision: D76951243 |
This PR needs a
|
Summary: - Fix non-HF style RoPE. - Support QK norm after RoPE. Differential Revision: D76951243
|
This pull request was exported from Phabricator. Differential Revision: D76951243 |
Summary: - Fix non-HF style RoPE. - Support QK norm after RoPE. Differential Revision: D76951243
|
This pull request was exported from Phabricator. Differential Revision: D76951243 |
Summary: - Fix non-HF style RoPE. - Support QK norm after RoPE. - Update tests to initialize QK norm weights for better coverage. Reviewed By: billmguo Differential Revision: D76951243
|
This pull request was exported from Phabricator. Differential Revision: D76951243 |
Differential Revision: D76951243 Pull Request resolved: pytorch#11808
Differential Revision: D76951243