Skip to content

per_channel_group can't be dynamic #9934

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 1 commit into from
Apr 7, 2025

Conversation

mcr229
Copy link
Contributor

@mcr229 mcr229 commented Apr 7, 2025

Summary: There are some dynamism issues that arise when checking the semantics of quantize_affine nodes. We avoid them by accounting for free_symbols.

Differential Revision: D72488540

Summary: There are some dynamism issues that arise when checking the semantics of quantize_affine nodes. We avoid them by accounting for free_symbols.

Differential Revision: D72488540
@mcr229 mcr229 requested a review from digantdesai as a code owner April 7, 2025 17:34
Copy link

pytorch-bot bot commented Apr 7, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/9934

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

✅ No Failures

As of commit eb44899 with merge base 2d56897 (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 Apr 7, 2025
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D72488540

Copy link
Contributor

@digantdesai digantdesai 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, we need to be more precise in the code and in the comments/docs about the word dynamic. We have dynamic shape, dynamic quant, dynamic weights (RHS in bmm in xnnpack), dynamic config. Just easy to assume the wrong one.

@mcr229
Copy link
Contributor Author

mcr229 commented Apr 7, 2025

@digantdesai yea lol, it can definitely be confusing for folks. I wonder if there are more precise terms we can use to describe the different natures of dynamism. I guess we can add qualifiers like dynamic quantization, dynamic shape, dynamic weights, etc..

@facebook-github-bot facebook-github-bot merged commit 68c84cc into pytorch:main Apr 7, 2025
83 of 86 checks passed
kirklandsign pushed a commit that referenced this pull request Apr 11, 2025
Differential Revision: D72488540

Pull Request resolved: #9934
keyprocedure pushed a commit to keyprocedure/executorch that referenced this pull request Apr 21, 2025
Differential Revision: D72488540

Pull Request resolved: pytorch#9934
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.

3 participants