Skip to content

feat: support aten.copy dynamo converter #2550

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

Merged
merged 3 commits into from
Jan 2, 2024

Conversation

zewenli98
Copy link
Collaborator

Description

Support aten.copy dynamo converter.

Fixes #2435

Type of change

  • New feature (non-breaking change which adds functionality)

Checklist:

  • My code follows the style guidelines of this project (You can use the linters)
  • I have performed a self-review of my own code
  • I have commented my code, particularly in hard-to-understand areas and hacks
  • I have made corresponding changes to the documentation
  • I have added tests to verify my fix or my feature
  • New and existing unit tests pass locally with my changes
  • I have added the relevant labels to my PR in so that relevant reviewers are notified

@github-actions github-actions bot added component: api [Python] Issues re: Python API component: conversion Issues re: Conversion stage component: dynamo Issues relating to the `torch.compile` or `torch._dynamo.export` paths component: tests Issues re: Tests labels Dec 18, 2023
@github-actions github-actions bot requested a review from peri044 December 18, 2023 23:55
Comment on lines +2560 to +2574
return impl.cast.to_copy(
ctx,
target,
SourceIR.ATEN,
name,
src,
src.dtype,
force_layer=True,
)
Copy link
Collaborator

Choose a reason for hiding this comment

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

The force_layer=True does seem useful for the purpose of the test case, but in a normal model we should prefer force_layer=False. This should be a future feature, but to_copy should have an intelligent force_layer mechanism which can select whether to insert the layer based on whether the node is an input node to the TRTEngine.

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Yes, I agree with you, but for now TensorRT doesn't support the same input and output.

Copy link
Collaborator

Choose a reason for hiding this comment

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

I added #2561 to track this proposed feature (in Torch-TRT)

@zewenli98 zewenli98 force-pushed the copy_dynamo_converter branch from cd735dc to 05e02c0 Compare December 28, 2023 16:20
Comment on lines +2560 to +2574
return impl.cast.to_copy(
ctx,
target,
SourceIR.ATEN,
name,
src,
src.dtype,
force_layer=True,
)
Copy link
Collaborator

Choose a reason for hiding this comment

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

I added #2561 to track this proposed feature (in Torch-TRT)

Copy link
Collaborator

@gs-olive gs-olive left a comment

Choose a reason for hiding this comment

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

Looks good to me!

@zewenli98 zewenli98 merged commit a42dfb3 into pytorch:main Jan 2, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
cla signed component: api [Python] Issues re: Python API component: conversion Issues re: Conversion stage component: dynamo Issues relating to the `torch.compile` or `torch._dynamo.export` paths component: tests Issues re: Tests
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Add support for aten.copy
3 participants