Skip to content

Conversation

@billmguo
Copy link
Contributor

Summary: add neg ops and annonation of to.dtype

Differential Revision: D68815927

@pytorch-bot
Copy link

pytorch-bot bot commented Jan 29, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/8041

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

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

✅ No Failures

As of commit 511d3f3 with merge base e63c923 (image):
💚 Looks good so far! There are no failures yet. 💚

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 Jan 29, 2025
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D68815927

@billmguo
Copy link
Contributor Author

@pytorchbot label "topic: not user facing"

billmguo added a commit to billmguo/executorch that referenced this pull request Jan 30, 2025
Summary:
pytorch#8041
add neg ops and annonation of to.dtype

Differential Revision: D68815927
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D68815927

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D68815927

billmguo added a commit to billmguo/executorch that referenced this pull request Jan 30, 2025
Summary:

pytorch#8041
add neg ops and annonation of to.dtype

Differential Revision: D68815927
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D68815927

billmguo added a commit to billmguo/executorch that referenced this pull request Jan 30, 2025
Summary:

pytorch#8041
add neg ops and annonation of to.dtype

Differential Revision: D68815927
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D68815927

billmguo added a commit to billmguo/executorch that referenced this pull request Jan 31, 2025
Summary:

pytorch#8041
add neg ops and annonation of to.dtype

Differential Revision: D68815927
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D68815927

billmguo added a commit to billmguo/executorch that referenced this pull request Jan 31, 2025
Summary:

pytorch#8041
add neg ops and annonation of to.dtype

Differential Revision: D68815927
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D68815927

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

This pull request was exported from Phabricator. Differential Revision: D68815927

billmguo added a commit to billmguo/executorch that referenced this pull request Jan 31, 2025
Summary:
Pull Request resolved: pytorch#8041

pytorch#8041
add neg ops and annonation of to.dtype

Differential Revision: D68815927
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D68815927

billmguo added a commit to billmguo/executorch that referenced this pull request Jan 31, 2025
Summary:
Pull Request resolved: pytorch#8041

pytorch#8041
add neg ops and annonation of to.dtype

Reviewed By: Andriyluck

Differential Revision: D68815927
@billmguo
Copy link
Contributor Author

billmguo commented Feb 3, 2025

@shewu-quic would u mind review and approve I will remove to.dypte ops since I modify model it can eliminate the to.dtype

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D68815927

billmguo added a commit to billmguo/executorch that referenced this pull request Feb 3, 2025
Summary:
Pull Request resolved: pytorch#8041

pytorch#8041
add neg ops and annonation of to.dtype

Reviewed By: Andriyluck

Differential Revision: D68815927
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D68815927

billmguo added a commit to billmguo/executorch that referenced this pull request Feb 3, 2025
Summary:
Pull Request resolved: pytorch#8041

pytorch#8041
add neg ops and annonation of to.dtype

Reviewed By: Andriyluck

Differential Revision: D68815927
Copy link
Collaborator

@shewu-quic shewu-quic left a comment

Choose a reason for hiding this comment

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

@winskuo-quic, could you help to review this PR about CI

image_dataset: str = ""
pretrained_weight: str = ""
enable_profile: bool = False
compile_only: bool = True
Copy link
Collaborator

Choose a reason for hiding this comment

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

It seems to be duplicated

enable_x86_64: bool = False
enable_x86_64: bool = True
compile_only: bool = False
dump_intermediate_outputs: bool = False
Copy link
Collaborator

Choose a reason for hiding this comment

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

May I know why do you need to add this variable?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

this is chen's test code. I re-base on top her pr to run the unit test in x86 emulator

)

output_dir = f"{tmp_dir}/outputs"
os.makedirs(output_dir, exist_ok=True)
Copy link
Collaborator

Choose a reason for hiding this comment

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

make_output_dir(output_dir)

use_16a4w: str = "16a4w"
shared_buffer: bool = False
enable_x86_64: bool = False
enable_x86_64: bool = True
Copy link
Collaborator

Choose a reason for hiding this comment

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

May I know why we need to set enable_x86_64 to True?

return self.pool(self.conv(x))


class Conv2dArgmin(torch.nn.Module):
Copy link
Collaborator

Choose a reason for hiding this comment

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

Conv2dArgmin should be in front of Conv2dAvgPool2d based on alphabetical order.

billmguo added a commit to billmguo/executorch that referenced this pull request Feb 3, 2025
Summary:

pytorch#8041
add neg ops and annonation of to.dtype

Reviewed By: Andriyluck

Differential Revision: D68815927
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D68815927

Copy link
Collaborator

@shewu-quic shewu-quic left a comment

Choose a reason for hiding this comment

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

LGTM. Thanks.

billmguo added a commit to billmguo/executorch that referenced this pull request Feb 4, 2025
Summary:

pytorch#8041
add neg ops and annonation of to.dtype

Reviewed By: Andriyluck

Differential Revision: D68815927
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D68815927

Copy link
Collaborator

@shewu-quic shewu-quic left a comment

Choose a reason for hiding this comment

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

LGTM. Thanks!

Summary:

pytorch#8041
add neg ops and annonation of to.dtype

Reviewed By: Andriyluck

Differential Revision: D68815927
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D68815927

@facebook-github-bot facebook-github-bot merged commit 9832db9 into pytorch:main Feb 5, 2025
46 of 47 checks passed
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 topic: not user facing

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants