Skip to content

Qualcomm AI Engine Direct - support dim_order #7189

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
Dec 5, 2024
Merged

Qualcomm AI Engine Direct - support dim_order #7189

merged 1 commit into from
Dec 5, 2024

Conversation

haowhsu-quic
Copy link
Collaborator

Summary

  • remove _to_dim op and let backend take care of tensor layout
    • Current layout_transform works well.
    • We always use contiguous memory to fetch parameters.
    • Remove this memory format operator won't affect the original output.
  • test cases

Fixes #<4873>

Test plan

python backends/qualcomm/tests/test_qnn_delegate.py -k TestQNNQuantizedOperators.test_qnn_backend_conv2d_channel_last -s $DEVICE_SERIAL -m $SOC_MODEL -b build-android/ -a $PATH_TO_ARTIFACTS

@haowhsu-quic
Qualcomm AI Engine Direct - support dim_order
6f54df9 
Summary
- remove _to_dim op and let backend take care of tensor layout
- test cases
@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Dec 5, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/7189

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

❌ 1 New Failure

As of commit 6f54df9 with merge base 8861b9a (image):

NEW FAILURE - The following job has failed:

  • pull / unittest-arm / linux-job (gh)
    RuntimeError: Command docker exec -t 01c02038e819a0c5d8cc8c6b785e054635c349a6e2c426d5afc85740d9284226 /exec failed with exit code 1

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 Dec 5, 2024
@dbort dbort requested review from Gasoonjia, swolchok and cccclai and removed request for swolchok December 5, 2024 07:12
@cccclai cccclai added partner: qualcomm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm release notes: backends [DO NOT USE] Changes to any of the backend delegates feature labels Dec 5, 2024
@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 9289b3f into pytorch:main Dec 5, 2024
42 of 45 checks passed
@digantdesai digantdesai mentioned this pull request Dec 9, 2024
Open
@haowhsu-quic haowhsu-quic deleted the dev_dim_order branch February 7, 2025 09:21
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@Gasoonjia Gasoonjia Gasoonjia approved these changes

@cccclai cccclai Awaiting requested review from cccclai cccclai is a code owner

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. partner: qualcomm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm release notes: backends [DO NOT USE] Changes to any of the backend delegates
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

Call for Action: Supporting Dim Order in Backend Delegates
4 participants
@haowhsu-quic @facebook-github-bot @Gasoonjia @cccclai