Skip to content

Conversation

@martinlsm
Copy link
Collaborator

@martinlsm martinlsm commented Oct 21, 2025

Besides having obsolete names, ReplaceScalarWithTensorPassTOSAMI and ReplaceScalarWithTensorPassTOSABI was causing difficulties for defining chronological pass dependencies with the _passes_required_after attribute. This is because, with the current design, there is no way to distinguish which profile is referred to when defining _passes_required_after; a pass simply declares its chronological dependencies globally.

Solve this by merging the two pass classes together into one called ReplaceScalarWithTensorByProfilePass. This means that a pass should include this new pass in _passes_required_after no matter which TOSA profile its working towards.

Test plan

This is a refactoring patch. No behavior is modified. Thus the tests already in place are enough to test this change.

cc @freddan80 @per @zingo @oscarandersson8218 @digantdesai

Besides having obsolete names, ReplaceScalarWithTensorPassTOSAMI and
ReplaceScalarWithTensorPassTOSABI was causing difficulties for defining
chronological pass dependencies with the `_passes_required_after`
attribute. This is because, with the current design, there is no way to
distinguish which profile is referred to when defining
`_passes_required_after`; a pass simply declares its chronological
dependencies globally.

Solve this by merging the two pass classes together into one called
`ReplaceScalarWithTensorByProfilePass`. This means that a pass should
include this new pass in `_passes_required_after` no matter which TOSA
profile its working towards.

Signed-off-by: Martin Lindström <[email protected]>
Change-Id: I00c0e3658426fb5c1da996eeee89093a395630db
@meta-cla meta-cla 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 Oct 21, 2025
@pytorch-bot
Copy link

pytorch-bot bot commented Oct 21, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/15298

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

❌ 8 New Failures, 3 Unrelated Failures

As of commit 2e398ab with merge base f7ca57e (image):

NEW FAILURES - The following jobs have failed:

FLAKY - The following jobs failed but were likely due to flakiness present on trunk:

BROKEN TRUNK - The following job failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@martinlsm
Copy link
Collaborator Author

@pytorchbot label ciflow/trunk

@martinlsm
Copy link
Collaborator Author

@pytorchbot label "partner: arm"

@pytorch-bot pytorch-bot bot added the partner: arm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Arm label Oct 21, 2025
@oscarandersson8218 oscarandersson8218 added the release notes: none Do not include this in the release notes label Oct 24, 2025
Copy link
Collaborator

@oscarandersson8218 oscarandersson8218 left a comment

Choose a reason for hiding this comment

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

Unrelated failures

@oscarandersson8218 oscarandersson8218 merged commit de56c81 into pytorch:main Oct 24, 2025
297 of 308 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ciflow/trunk CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. partner: arm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Arm release notes: none Do not include this in the release notes

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants