Arm backend: Add tests for Stable Diffusion 3.5 Large model - #22606
Merged
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/22606
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit fbb9ccc with merge base 78c85d7 ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
|
|
Contributor
Author
|
@pytorchbot label "partner: arm" |
pytorch-bot
Bot
added
the
partner: arm
Contributor
Author
|
@pytorchbot label "release notes: arm" |
FabulousSuperDude
marked this pull request as ready for review
September 8, 2026 15:57
FabulousSuperDude
force-pushed
the
sd35_test
branch
from
September 8, 2026 15:57
a7b8e3d to
fbe8f10
Compare
zingo
approved these changes
Sep 8, 2026
FabulousSuperDude
force-pushed
the
sd35_test
branch
from
September 9, 2026 10:57
fbe8f10 to
aa3158b
Compare
- Add SD3.5 Large test configs for CLIP text encoders, T5 text encoder, MMDiT transformer, and VAE decoder, with optional upstream-sync validation. - Add Arm backend lowering tests for CLIP-L, CLIP-bigG, T5, transformer, and VAE decoder components across TOSA and VGF pipelines. - Add wrapper and model-loader unit tests covering wrapper output signatures, component subfolder loading, selective component loading, and dummy input shape generation. Signed-off-by: Sangwon Ha <sangwon.ha@arm.com> Change-Id: Id7a58f7046c17b33875ee9ef1ffa9050fa41e207
Enable TOSA reference-model execution for the T5 floating-point test. Share an int64-to-int32 pass factory between the CLIP and T5 tests, creating fresh pass instances for each pipeline. Set qtol=2 for the quantized VAE VGF test to accommodate cross-platform VKML rounding differences. Signed-off-by: Sangwon Ha <sangwon.ha@arm.com> Change-Id: I73d0ce40410766ab010e6e7410521aaadfa35a78
FabulousSuperDude
force-pushed
the
sd35_test
branch
from
September 9, 2026 10:59
84f2992 to
fbb9ccc
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
cc @digantdesai @freddan80 @per @zingo @oscarandersson8218 @mansnils @Sebastian-Larsson @robell @rascani