Skip to content

Qualcomm AI Engine Direct - XR model enablement pipe_clean #8299

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 1 commit into from
Feb 14, 2025
Merged

Qualcomm AI Engine Direct - XR model enablement pipe_clean #8299

merged 1 commit into from
Feb 14, 2025

Conversation

haowhsu-quic
Copy link
Collaborator

@haowhsu-quic haowhsu-quic commented Feb 7, 2025 •
edited
Loading

Summary

  • support linalg_vector_norm, instance_norm, any, not_equal, full
  • expand coverage of quantization annotator
  • test cases
  • small refactor for _pass importing

Test plan

python backends/qualcomm/tests/test_qnn_delegate.py -k TestQNNQuantizedOperator -s $DEVICE_SERIAL -m SM8650 -b build-android/

@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Feb 7, 2025 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/8299

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

✅ You can merge normally! (1 Unrelated Failure)

As of commit 67a1622 with merge base 433e30b (image):

BROKEN TRUNK - The following job failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

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 Feb 7, 2025
@haowhsu-quic
Copy link
Collaborator Author

@pytorchbot label "release notes: qualcomm"

@pytorch-bot pytorch-bot bot added the release notes: qualcomm Changes to the Qualcomm backend delegate label Feb 7, 2025
@haowhsu-quic haowhsu-quic force-pushed the dev_xr_model_pipe_clean branch from a288a59 to 79506fc Compare February 10, 2025 15:17
@haowhsu-quic haowhsu-quic mentioned this pull request Feb 11, 2025
Merged
@facebook-github-bot
Copy link
Contributor

@cccclai has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

@cccclai cccclai self-requested a review February 11, 2025 05:47
cccclai
cccclai approved these changes Feb 11, 2025
View reviewed changes
Copy link
Contributor

@cccclai cccclai left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you!

backends/qualcomm/_passes/decompose_linalg_vector_norm.py
return torch.pow(x, 1.0 / self.exp)


class DecomposeLinalgVectorNorm(ExportPass):
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Seems like there are lots engineer work here, maybe we (ExecuTorch side) should figure out how to make it simpler

@cccclai
Copy link
Contributor

cccclai commented Feb 11, 2025

This PR needs to rebase. Can you help with that?

@github-actions github-actions bot mentioned this pull request Feb 11, 2025
Open
@haowhsu-quic haowhsu-quic force-pushed the dev_xr_model_pipe_clean branch from 87a3932 to 66a679f Compare February 12, 2025 16:19
@facebook-github-bot
Copy link
Contributor

@cccclai has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

@cccclai
Copy link
Contributor

cccclai commented Feb 12, 2025

Hmm, I feel like the diff train is not catching up...will come back to this PR (maybe 1-2 days) and see if it's in a good state

@cccclai
Copy link
Contributor

cccclai commented Feb 13, 2025

The diff train is good now, mind rebasing?

@haowhsu-quic
Qualcomm AI Engine Direct - XR model enablement pipe_clean
67a1622 
summary
- support linalg_vector_norm, instance_norm, any, ne
- expand coverage of quantization annotator
- test cases
- small refactor for _pass importing
@haowhsu-quic haowhsu-quic force-pushed the dev_xr_model_pipe_clean branch from 66a679f to 67a1622 Compare February 14, 2025 06:06
@facebook-github-bot
Copy link
Contributor

@cccclai has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

@cccclai cccclai merged commit d0b74cb into pytorch:main Feb 14, 2025
47 of 48 checks passed
@github-actions github-actions bot mentioned this pull request Feb 17, 2025
Open
@github-actions github-actions bot mentioned this pull request Feb 24, 2025
Open
@shewu-quic shewu-quic mentioned this pull request Feb 25, 2025
Closed
@github-actions github-actions bot mentioned this pull request Mar 3, 2025
Open
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. release notes: qualcomm Changes to the Qualcomm backend delegate
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@haowhsu-quic @facebook-github-bot @cccclai