Skip to content

[ET] correcting cpu ref quantize_per_channel logic to align with ATen #12203

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 8 commits into from
Jul 14, 2025

Conversation

ahmtox
Copy link
Contributor

@ahmtox ahmtox commented Jul 3, 2025

Stack from ghstack (oldest at bottom):

Context

The quantize_per_channel was not perfectly aligned with the ATen implementation, and demonstrated errors when specifying different axis. This bug wasn't distinctly acknowledged given that the test cases only has one test for the whole operator. In order to align more closely with ATen this change simply does a single loop imlpementation with direct channel index calculation over the old apply_over_dim_list approach.

Changes

We change the core logic for quantize_per_channel to more properly align with ATen's implementation, and we also change it from apply_over_dim_list approach to a single loop implementation with direct channel index calculation. This also adds more comprehensive testing for quantize_per_channel so that a bug isn't missed again.

Differential Revision: D77746130

# Context

The quantize_per_channel was not perfectly aligned with the ATen implementation, and demonstrated errors when specifying different axis. This bug wasn't distinctly acknowledged given that the test cases only has one test for the whole operator. In order to align more closely with ATen this change simply does a single loop imlpementation with direct channel index calculation over the old `apply_over_dim_list` approach.

# Changes

We change the core logic for quantize_per_channel to more properly align with ATen's implementation, and we also change it from `apply_over_dim_list` approach to a single loop implementation with direct channel index calculation. This also adds more comprehensive testing for quantize_per_channel so that a bug isn't missed again.

Differential Revision: [D77746130](https://our.internmc.facebook.com/intern/diff/D77746130/)

[ghstack-poisoned]
Copy link

pytorch-bot bot commented Jul 3, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/12203

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

❌ 2 New Failures, 3 Unrelated Failures

As of commit 6c79860 with merge base 1540659 (image):

NEW FAILURES - The following jobs have failed:

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

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

Copy link

github-actions bot commented Jul 3, 2025

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

@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 Jul 3, 2025
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D77746130

…n with ATen"

# Context

The quantize_per_channel was not perfectly aligned with the ATen implementation, and demonstrated errors when specifying different axis. This bug wasn't distinctly acknowledged given that the test cases only has one test for the whole operator. In order to align more closely with ATen this change simply does a single loop imlpementation with direct channel index calculation over the old `apply_over_dim_list` approach.

# Changes

We change the core logic for quantize_per_channel to more properly align with ATen's implementation, and we also change it from `apply_over_dim_list` approach to a single loop implementation with direct channel index calculation. This also adds more comprehensive testing for quantize_per_channel so that a bug isn't missed again.

Differential Revision: [D77746130](https://our.internmc.facebook.com/intern/diff/D77746130/)

[ghstack-poisoned]
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D77746130

…n with ATen"

# Context

The quantize_per_channel was not perfectly aligned with the ATen implementation, and demonstrated errors when specifying different axis. This bug wasn't distinctly acknowledged given that the test cases only has one test for the whole operator. In order to align more closely with ATen this change simply does a single loop imlpementation with direct channel index calculation over the old `apply_over_dim_list` approach.

# Changes

We change the core logic for quantize_per_channel to more properly align with ATen's implementation, and we also change it from `apply_over_dim_list` approach to a single loop implementation with direct channel index calculation. This also adds more comprehensive testing for quantize_per_channel so that a bug isn't missed again.

Differential Revision: [D77746130](https://our.internmc.facebook.com/intern/diff/D77746130/)

[ghstack-poisoned]
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D77746130

…n with ATen"

# Context

The quantize_per_channel was not perfectly aligned with the ATen implementation, and demonstrated errors when specifying different axis. This bug wasn't distinctly acknowledged given that the test cases only has one test for the whole operator. In order to align more closely with ATen this change simply does a single loop imlpementation with direct channel index calculation over the old `apply_over_dim_list` approach.

# Changes

We change the core logic for quantize_per_channel to more properly align with ATen's implementation, and we also change it from `apply_over_dim_list` approach to a single loop implementation with direct channel index calculation. This also adds more comprehensive testing for quantize_per_channel so that a bug isn't missed again.

Differential Revision: [D77746130](https://our.internmc.facebook.com/intern/diff/D77746130/)

[ghstack-poisoned]
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D77746130

…n with ATen"

# Context

The quantize_per_channel was not perfectly aligned with the ATen implementation, and demonstrated errors when specifying different axis. This bug wasn't distinctly acknowledged given that the test cases only has one test for the whole operator. In order to align more closely with ATen this change simply does a single loop imlpementation with direct channel index calculation over the old `apply_over_dim_list` approach.

# Changes

We change the core logic for quantize_per_channel to more properly align with ATen's implementation, and we also change it from `apply_over_dim_list` approach to a single loop implementation with direct channel index calculation. This also adds more comprehensive testing for quantize_per_channel so that a bug isn't missed again.

Differential Revision: [D77746130](https://our.internmc.facebook.com/intern/diff/D77746130/)

[ghstack-poisoned]
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D77746130

…n with ATen"

# Context

The quantize_per_channel was not perfectly aligned with the ATen implementation, and demonstrated errors when specifying different axis. This bug wasn't distinctly acknowledged given that the test cases only has one test for the whole operator. In order to align more closely with ATen this change simply does a single loop imlpementation with direct channel index calculation over the old `apply_over_dim_list` approach.

# Changes

We change the core logic for quantize_per_channel to more properly align with ATen's implementation, and we also change it from `apply_over_dim_list` approach to a single loop implementation with direct channel index calculation. This also adds more comprehensive testing for quantize_per_channel so that a bug isn't missed again.

Differential Revision: [D77746130](https://our.internmc.facebook.com/intern/diff/D77746130/)

[ghstack-poisoned]
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D77746130

…n with ATen"

# Context

The quantize_per_channel was not perfectly aligned with the ATen implementation, and demonstrated errors when specifying different axis. This bug wasn't distinctly acknowledged given that the test cases only has one test for the whole operator. In order to align more closely with ATen this change simply does a single loop imlpementation with direct channel index calculation over the old `apply_over_dim_list` approach.

# Changes

We change the core logic for quantize_per_channel to more properly align with ATen's implementation, and we also change it from `apply_over_dim_list` approach to a single loop implementation with direct channel index calculation. This also adds more comprehensive testing for quantize_per_channel so that a bug isn't missed again.

Differential Revision: [D77746130](https://our.internmc.facebook.com/intern/diff/D77746130/)

[ghstack-poisoned]
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D77746130

…n with ATen"

# Context

The quantize_per_channel was not perfectly aligned with the ATen implementation, and demonstrated errors when specifying different axis. This bug wasn't distinctly acknowledged given that the test cases only has one test for the whole operator. In order to align more closely with ATen this change simply does a single loop imlpementation with direct channel index calculation over the old `apply_over_dim_list` approach.

# Changes

We change the core logic for quantize_per_channel to more properly align with ATen's implementation, and we also change it from `apply_over_dim_list` approach to a single loop implementation with direct channel index calculation. This also adds more comprehensive testing for quantize_per_channel so that a bug isn't missed again.

Differential Revision: [D77746130](https://our.internmc.facebook.com/intern/diff/D77746130/)

[ghstack-poisoned]
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D77746130

@facebook-github-bot facebook-github-bot merged commit 796d79f into gh/ahmtox/31/base Jul 14, 2025
94 of 100 checks passed
@facebook-github-bot facebook-github-bot deleted the gh/ahmtox/31/head branch July 14, 2025 14:58
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
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants