Skip to content

conv1d fix #411

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

Closed
wants to merge 1 commit into from
Closed

conv1d fix #411

wants to merge 1 commit into from

Conversation

kirklandsign
Copy link
Contributor

Summary:
Fix conv1d to handle both unlifted=True and unlifted=False.

When unlifted is False, we need to update the node for the parameter. setattr doesn't work there.

In a follow-up diff, we add that to torch._export.utils

Differential Revision: D49428868

@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 19, 2023
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D49428868

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D49428868

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

This pull request was exported from Phabricator. Differential Revision: D49428868

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D49428868

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D49428868

Summary:

Fix conv1d to handle both unlifted=True and unlifted=False.

When unlifted is False, we need to update the node for the parameter. `setattr` doesn't work there.

In a follow-up diff, we add that to torch._export.utils

Reviewed By: digantdesai

Differential Revision: D49428868
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D49428868

@facebook-github-bot
Copy link
Contributor

This pull request has been merged in 96b83ce.

Gasoonjia pushed a commit that referenced this pull request Jul 30, 2024
This reverts commit 052fb1a3792123e291fb5f47084644913c8ecba7 to  fix [test-tinystories-executorch](https://github.com/pytorch/torchchat/actions/runs/8802811768/job/24159454773?pr=411#logs)
Gasoonjia pushed a commit that referenced this pull request Jul 30, 2024
* Revert "Revert "Embedding quantization per backend (#402)" (#411)"

This reverts commit 8b35acdff4fded779799ab8a419e55f885dd8918.

* 4b and 8b embedding table quantization

* minor changes

* remove extra et workflow
Gasoonjia pushed a commit that referenced this pull request Jul 30, 2024
* Revert "Revert "Embedding quantization per backend (#402)" (#411)"

This reverts commit 8b35acdff4fded779799ab8a419e55f885dd8918.

* merge GGUF tests into pull.yml
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
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
Development

Successfully merging this pull request may close these issues.

2 participants