Skip to content

Arm backend: Add VGF tests to StableDiffusion module tests#14655

Merged
zingo merged 2 commits intopytorch:mainfrom
YufengShi-dudu:add-vgf-tests-for-stable-diffusion
Oct 2, 2025
Merged

Arm backend: Add VGF tests to StableDiffusion module tests#14655
zingo merged 2 commits intopytorch:mainfrom
YufengShi-dudu:add-vgf-tests-for-stable-diffusion

Conversation

@YufengShi-dudu
Copy link
Copy Markdown
Collaborator

@YufengShi-dudu YufengShi-dudu commented Sep 29, 2025

Also refactor the StableDiffusion module tests to use test_pipeline instead of ArmTester directly.

Change-Id: Iac07da7edc5a638d95c9bb6ad4b134c44aedac05

cc @digantdesai @freddan80 @per @zingo @oscarandersson8218

Also refactor the StableDiffusion module tests to use test_pipeline
instead of ArmTester directly.

Change-Id: Iac07da7edc5a638d95c9bb6ad4b134c44aedac05
Signed-off-by: Yufeng Shi <yufeng.shi@arm.com>
@YufengShi-dudu YufengShi-dudu added partner: arm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Arm ciflow/trunk release notes: none Do not include this in the release notes labels Sep 29, 2025
@pytorch-bot
Copy link
Copy Markdown

pytorch-bot Bot commented Sep 29, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14655

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

❌ 2 New Failures, 3 Unrelated Failures

As of commit b6a572d with merge base 049c9fc (image):

NEW FAILURES - The following jobs have failed:

FLAKY - The following job failed but was likely due to flakiness present on trunk:

BROKEN TRUNK - The following jobs failed but was 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.

@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 29, 2025
exir_op=[],
tosa_version="TOSA-1.0+FP",
use_to_edge_transform_and_lower=True,
atol=4, # TODO: Investiage numerical issue: MAX Diff ~50%
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

Let's make sure this test isn't flaky.

Copy link
Copy Markdown
Collaborator Author

Choose a reason for hiding this comment

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

Yes, that's a good point. I tested it locally and 4 should be enough. But we can increase it later if we see flaky issue upstream.

@zingo zingo merged commit 499ce50 into pytorch:main Oct 2, 2025
274 of 279 checks passed
jirioc pushed a commit to nxp-upstream/executorch that referenced this pull request Dec 19, 2025
…4655)

Also refactor the StableDiffusion module tests to use test_pipeline
instead of ArmTester directly.

Signed-off-by: Yufeng Shi <yufeng.shi@arm.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ciflow/trunk CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. partner: arm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Arm release notes: none Do not include this in the release notes

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants