Skip to content

Qualcomm AI Engine Direct - Fix aihub path failing due to memory planning pass #5482

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
Closed
wants to merge 1 commit into from
Closed

Qualcomm AI Engine Direct - Fix aihub path failing due to memory planning pass #5482

wants to merge 1 commit into from

Conversation

winskuo-quic
Copy link
Collaborator

Summary

Update MemoryPlanningPass to use default greedy algo.

@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Sep 19, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/5482

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

✅ No Failures

As of commit c2564e8 with merge base 5a984cc (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 Sep 19, 2024
@winskuo-quic
Copy link
Collaborator Author

Hi @cccclai,
Newest Mainline is causing QAIHUB flow to fail due to change of interface for MemoryPlanningPass.
Please have a look.
Thanks

@winskuo-quic
Copy link
Collaborator Author

Hi @cccclai,

I wanted to follow up on this PR, which all QAIHub scripts will fail in current mainline.
Your feedback is greatly appreciated.

Thanks for your time!

@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 Sep 23, 2024

Hi sorry was in the conference for the past few days. Any chance we know why it's failing? When does it start to fail?

cccclai
cccclai reviewed Sep 23, 2024
View reviewed changes
examples/qualcomm/qaihub_scripts/utils/utils.py
for pte_name in pte_names:
print(f"{pte_name} generating...")
memory_planning_pass = MemoryPlanningPass(
memory_planning_algo="greedy",
Copy link
Contributor

Choose a reason for hiding this comment

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

The default algo is greedy and I'm not sure how this line will fix the issue. Could you elaborate a bit more?

@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 Sep 23, 2024

Actually nvm, just saw #4727

@winskuo-quic
Copy link
Collaborator Author

Hi sorry was in the conference for the past few days. Any chance we know why it's failing? When does it start to fail?

All good and thanks a lot for reviewing.
As you mentioned above, #4727 is causing the failure.

@cccclai
Copy link
Contributor

cccclai commented Sep 24, 2024

hey mind rebasing the PR? Somehow the tests are not running

@winskuo-quic winskuo-quic force-pushed the dev1/winskuo/fix_memory_planning_pass branch from 291abd1 to c2564e8 Compare September 24, 2024 01:31
@winskuo-quic
Copy link
Collaborator Author

winskuo-quic commented Sep 24, 2024 •
edited
Loading

hey mind rebasing the PR? Somehow the tests are not running

Just rebased to the mainline.
Thanks

@facebook-github-bot
Copy link
Contributor

@cccclai merged this pull request in 90dcea5.

@cccclai
Copy link
Contributor

cccclai commented Sep 30, 2024

@pytorchbot cherry-pick --onto release/0.4 -c regression

pytorchbot pushed a commit that referenced this pull request Sep 30, 2024
@winskuo-quic @pytorchbot
Qualcomm AI Engine Direct - Fix aihub path failing due to memory plan…
485248b 
…ning pass (#5482)

Summary:
Update MemoryPlanningPass to use default greedy algo.

Pull Request resolved: #5482

Reviewed By: kirklandsign

Differential Revision: D63270305

Pulled By: cccclai

fbshipit-source-id: 7fb03365e3cadb53e4879feb7f105aadc9e9497c
(cherry picked from commit 90dcea5)
@pytorchbot
Copy link
Collaborator

Cherry picking #5482

The cherry pick PR is at #5748 and it is recommended to link a regression cherry pick PR with an issue. The following tracker issues are updated:

Details for Dev Infra team Raised by workflow job

@pytorchbot pytorchbot mentioned this pull request Sep 30, 2024
Closed
jackzhxng pushed a commit that referenced this pull request Oct 10, 2024
@pytorchbot @winskuo-quic
Qualcomm AI Engine Direct - Fix aihub path failing due to memory plan…
6655c3b 
…ning pass (#5748)

Qualcomm AI Engine Direct - Fix aihub path failing due to memory planning pass (#5482)

Summary:
Update MemoryPlanningPass to use default greedy algo.

Pull Request resolved: #5482

Reviewed By: kirklandsign

Differential Revision: D63270305

Pulled By: cccclai

fbshipit-source-id: 7fb03365e3cadb53e4879feb7f105aadc9e9497c
(cherry picked from commit 90dcea5)

Co-authored-by: winskuo-quic <[email protected]>
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. Merged

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@winskuo-quic @facebook-github-bot @cccclai @pytorchbot