Skip to content

Qualcomm AI Engine Direct - fix suite op #15162

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.

Sign up for GitHub

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

Jump to bottom
Merged
merged 3 commits into from
Oct 28, 2025
Merged

Qualcomm AI Engine Direct - fix suite op #15162

merged 3 commits into from
Oct 28, 2025
+116 −27

Conversation

@haowhsu-quic
Copy link
Collaborator

@haowhsu-quic haowhsu-quic commented Oct 15, 2025 •
edited by pytorch-bot bot
Loading

Summary

  • fix annotation logic for non arithmetic op
  • partition out unsupported embedding_bag op
  • use calibration input in suite test when verifying quantized op

Test plan

e.g. pytest --disable-warnings -c /dev/nul backends/test/suite/ -k test_split_size_dimensions[qnn_16a16w]

cc @cccclai @cbilgin

@pytorch-bot
Copy link

pytorch-bot bot commented Oct 15, 2025 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/15162

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

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

❌ 1 New Failure

As of commit 9e6d72d with merge base 72b1fa1 (image):

NEW FAILURE - The following job has failed:

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

@github-actions
Copy link

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.

@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 15, 2025
@haowhsu-quic
Copy link
Collaborator Author

Hi @cccclai, if the framework change makes sense to you. I still need some time to test all the decoder models thoroughly since the annotation change of concat will somewhat impact the accuracy of kv_cache. Will ping you again once all of them are well tested.

@haowhsu-quic haowhsu-quic marked this pull request as ready for review October 21, 2025 17:19
@haowhsu-quic haowhsu-quic requested a review from cccclai as a code owner October 21, 2025 17:19
@cccclai
Copy link
Contributor

cccclai commented Oct 22, 2025

It seems like some tests are failing..

@haowhsu-quic haowhsu-quic marked this pull request as draft October 22, 2025 05:51
@haowhsu-quic
Qualcomm AI Engine Direct - fix suite op
bb806e6 
- fix annotation logic for non arithmetic op
- partition out unsupported embedding_bag op
- use calibration input in suite test when verifying quantized op
@haowhsu-quic haowhsu-quic marked this pull request as ready for review October 27, 2025 16:09
@digantdesai digantdesai added the module: qnn Issues related to Qualcomm's QNN delegate and code under backends/qualcomm/ label Oct 27, 2025
@cccclai cccclai merged commit c1c5a71 into pytorch:main Oct 28, 2025
144 of 145 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@cccclai cccclai cccclai approved these changes

Assignees

No one assigned

Labels

CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. module: qnn Issues related to Qualcomm's QNN delegate and code under backends/qualcomm/

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@haowhsu-quic @cccclai @digantdesai