Skip to content

NXP backend: Improve quantization annotation process #11908

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

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

robert-kalmar
Copy link
Collaborator

@robert-kalmar robert-kalmar commented Jun 24, 2025

Summary

Addresses multiple subsequent nodes with SharedSpecPattern problem.

cc @digantdesai @JakeStevens

Copy link

pytorch-bot bot commented Jun 24, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11908

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

✅ No Failures

As of commit 338c637 with merge base 75e4044 (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 Jun 24, 2025
- fixes multiple subsequent nodes with SharedSpecPattern problem
@StrycekSimon StrycekSimon force-pushed the upstream/main-nxp/EIEX-300-upstream-quantization-annotation-improvements branch from be6144f to 338c637 Compare July 1, 2025 07:05
@StrycekSimon
Copy link
Contributor

@pytorchbot label "module: nxp" "release notes: nxp"

@pytorch-bot pytorch-bot bot added module: nxp Issues related to NXP Neutron NPU delegation and code under backends/nxp/ release notes: nxp Changes to the NXP Neutron backend delegate labels Jul 1, 2025
@JakeStevens
Copy link
Contributor

Can you provide a little more info on what this is solving?

Perhaps a test to illustrate/prove that is now correct and ensure no regression later

@StrycekSimon
Copy link
Contributor

Since the SharedSpecPattern quantization pattern relies on quantization annotation from the previous node in the graph, we need to process the nodes in order. Changes present in this PR do exactly this.

I will add a test that covers this case.

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. module: nxp Issues related to NXP Neutron NPU delegation and code under backends/nxp/ release notes: nxp Changes to the NXP Neutron backend delegate
Projects
None yet
Development

Successfully merging this pull request may close these issues.

5 participants