Skip to content

Conversation

shewu-quic
Copy link
Collaborator

@shewu-quic shewu-quic commented Sep 3, 2025

Summary:

  • Fixed the seed for E2E model scripts in unit test
  • Resolved the bug during dump optrace
  • The per-channel quant config of the bias for conv op should be derived by activation and weight.
  • Resolve the issue caused by the PR that prevented the spec from being correctly updated to the quantized type.

@shewu-quic shewu-quic requested a review from cccclai as a code owner September 3, 2025 01:15
Copy link

pytorch-bot bot commented Sep 3, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/13892

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

❌ 1 New Failure

As of commit b78c552 with merge base fcdcd8e (image):

NEW FAILURE - The following job has failed:

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

@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 Sep 3, 2025
Copy link

github-actions bot commented Sep 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.

@shewu-quic
Copy link
Collaborator Author

Hi @cccclai ,
This PR is to resolve some errors in our internal unit test with ExecuTorch mainline and qnn 2.37.
Could you please take a look?
Thanks

@facebook-github-bot
Copy link
Contributor

@cccclai has imported this pull request. If you are a Meta employee, you can view this in D81602007.

@cccclai
Copy link
Contributor

cccclai commented Sep 3, 2025

It seems like static_llama_qnn test is failing, can you take a look

Summary:
  - Fixed the seed for E2E model scripts in unit test
  - Resolved the bug during dump optrace
  - The per-channel quant config of the bias for conv op should be derived by activation and weight.
  - Fixed the dtype in meta['spec'] for quantized io
@shewu-quic shewu-quic force-pushed the dev1/hutton/fix_ut_failed branch from 150f8ed to b78c552 Compare September 5, 2025 02:10
@shewu-quic
Copy link
Collaborator Author

It seems like static_llama_qnn test is failing, can you take a look

Thanks for reminder.
It seems like network issue to download llvm. It's ok after I rebased.

@facebook-github-bot
Copy link
Contributor

@cccclai has imported this pull request. If you are a Meta employee, you can view this in D81602007.

@cccclai cccclai merged commit bf22ab7 into pytorch:main Sep 8, 2025
116 of 118 checks passed
@mergennachin mergennachin mentioned this pull request Sep 8, 2025
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.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants