Skip to content

Enable W2L XNNPACK delegation #212

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

Enable W2L XNNPACK delegation #212

wants to merge 1 commit into from

Conversation

kirklandsign
Copy link
Contributor

Summary: Model is like conv->relu->conv->relu... -> log_softmax (not delegated at the moment)

Reviewed By: digantdesai

Differential Revision: D48872594

@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 5, 2023
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D48872594

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D48872594

3 similar comments
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D48872594

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D48872594

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D48872594

@huydhn huydhn mentioned this pull request Sep 12, 2023
Closed
facebook-github-bot pushed a commit that referenced this pull request Sep 12, 2023
@huydhn @facebook-github-bot
Allow each model to choose its own runner (#277)
89f3e39 
Summary:
It's a good idea to allow each model to choose its own runner.  This also help unblock #212 until we know the root cause of why it runs OOM.

Pull Request resolved: #277

Reviewed By: kirklandsign

Differential Revision: D49176509

Pulled By: huydhn

fbshipit-source-id: b5e74943fb62839e3b9a7ff132842c8614d0f84b
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D48872594

1 similar comment
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D48872594

@kirklandsign @facebook-github-bot
Enable W2L XNNPACK delegation (#212)
e78a1f0 
Summary:

[Model](https://pytorch.org/audio/main/_modules/torchaudio/models/wav2letter.html#Wav2Letter) is like conv->relu->conv->relu... -> log_softmax (not delegated at the moment)

Set _unlift=True in CaptureConfig because we have some issues with conv1d. Unblock for now and deploy on CI to prevent from further regression.

Reviewed By: digantdesai

Differential Revision: D48872594
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D48872594

1 similar comment
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D48872594

@facebook-github-bot
Copy link
Contributor

This pull request has been merged in c5fecc8.

Gasoonjia pushed a commit that referenced this pull request Jul 30, 2024
@mikekgfb @malfet
fixed device support for int4, and unit tests (#212)
1ff8d80 
* fixed device support for int4, and unit tests

* typo

* typo

* bfloat16 on macos

* bfloat16 in mps, redux

* typo

* remove extraneous use_cuda

* device setting in gguf loader
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
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 Merged
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@kirklandsign @facebook-github-bot