Skip to content
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

feat: support aten.isnan converter #2711

Merged
merged 2 commits into from
Apr 12, 2024
Merged

feat: support aten.isnan converter #2711

merged 2 commits into from
Apr 12, 2024

Conversation

chohk88
Copy link
Collaborator

@chohk88 chohk88 commented Mar 26, 2024

Description

In TRT, there isn't a direct way to check for NaN values, so I used a clever method. This method involves comparing the tensor to itself; input == input will only be false when dealing with NaN values.

Fixes # (issue)

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

@chohk88 chohk88 self-assigned this Mar 26, 2024
@github-actions github-actions bot added component: tests Issues re: Tests component: conversion Issues re: Conversion stage component: converters Issues re: Specific op converters component: api [Python] Issues re: Python API component: dynamo Issues relating to the `torch.compile` or `torch._dynamo.export` paths labels Mar 26, 2024
@github-actions github-actions bot requested a review from peri044 March 26, 2024 08:06
@chohk88 chohk88 linked an issue Mar 26, 2024 that may be closed by this pull request
Copy link
Collaborator

@zewenli98 zewenli98 left a comment

Choose a reason for hiding this comment

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

LGTM! Just one comment below.

input: TRTTensor,
) -> TRTTensor:
# False for NaN elements since NaN is not equal to anything, including itself.
equality_result = impl.elementwise.ops.eq(
Copy link
Collaborator

Choose a reason for hiding this comment

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

For consistency, you can directly call impl.elementwise.eq() because the eq is exposed.

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Thank you! I changed it!

Copy link
Collaborator

@zewenli98 zewenli98 left a comment

Choose a reason for hiding this comment

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

LGTM!

@narendasan narendasan merged commit 6a471b1 into main Apr 12, 2024
15 of 21 checks passed
@narendasan narendasan deleted the aten_isnan_converter branch April 12, 2024 00:47
peri044 pushed a commit that referenced this pull request Apr 19, 2024
laikhtewari pushed a commit that referenced this pull request May 24, 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: converters Issues re: Specific op converters 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.

aten.isnan
4 participants