Skip to content

[ExecuTorch] Add optimized op_linear #5124

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

Jump to bottom
Closed
wants to merge 1 commit into from
Closed

[ExecuTorch] Add optimized op_linear #5124

wants to merge 1 commit into from

Conversation

swolchok
Copy link
Contributor

@swolchok swolchok commented Sep 6, 2024 •
edited
Loading

@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Sep 6, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/5124

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

❌ 1 New Failure

As of commit 01b07b7 with merge base 2b50c76 (image):

NEW FAILURE - The following job has failed:

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

@facebook-github-bot facebook-github-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 Sep 6, 2024
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D62154007

This was referenced Sep 6, 2024
Merged
Closed
swolchok added a commit that referenced this pull request Sep 6, 2024
@swolchok
[ExecuTorch] Add optimized op_linear
98d55c5 
If we happen to be running without a delegate, directly implementing linear is much more efficient than permute_copy_out (materialize a transpose) followed by matmul.

Differential Revision: [D62154007](https://our.internmc.facebook.com/intern/diff/D62154007/)

ghstack-source-id: 241282447
Pull Request resolved: #5124
@swolchok swolchok changed the base branch from gh/swolchok/33/base to gh/swolchok/32/head September 6, 2024 00:13
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D62154007

This was referenced Sep 9, 2024
Closed
Closed
Closed
Closed
Closed
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D62154007

swolchok added a commit that referenced this pull request Sep 9, 2024
@swolchok
[ExecuTorch] Add optimized op_linear
e49b127 
Pull Request resolved: #5124

If we happen to be running without a delegate, directly implementing linear is much more efficient than permute_copy_out (materialize a transpose) followed by matmul.
ghstack-source-id: 241719570
@exported-using-ghexport

Differential Revision: [D62154007](https://our.internmc.facebook.com/intern/diff/D62154007/)
@kimishpatel
Copy link
Contributor

something is off with the stack. bunch of unrelated files are change. probably diff train related shenanigans?

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D62154007

kimishpatel
kimishpatel approved these changes Sep 10, 2024
View reviewed changes
Copy link
Contributor

@kimishpatel kimishpatel left a comment

Choose a reason for hiding this comment

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

stamping to unblock but @kirklandsign please see the clobbering happening from other unrelated changes

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D62154007

@swolchok @kirklandsign
[ExecuTorch] Add optimized op_linear
01b07b7 
If we happen to be running without a delegate, directly implementing linear is much more efficient than permute_copy_out (materialize a transpose) followed by matmul.

Differential Revision: [D62154007](https://our.internmc.facebook.com/intern/diff/D62154007/)

[ghstack-poisoned]
@swolchok
Copy link
Contributor Author

this stack needs re-export

@swolchok swolchok closed this Sep 10, 2024
@kirklandsign kirklandsign deleted the gh/swolchok/33/head branch September 11, 2024 21:10
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@kimishpatel kimishpatel kimishpatel 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. fb-exported

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@swolchok @facebook-github-bot @kimishpatel