Adding Models to Test Matrix for Zephyr CI Test #13193
Merged
Conversation
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/13193
Note: Links to docs will display an error until the docs builds have been completed. ❌ 3 New Failures, 19 Pending, 1 Unrelated FailureAs of commit b2a355e with merge base f7f486d ( NEW FAILURES - The following jobs have failed:
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. |
meta-cla
bot
added
the
CLA Signed
BujSet
added
ciflow/trunk
module: microcontrollers
Contributor
Author
|
@pytorchbot label "release notes: none" |
pytorch-bot
bot
added
the
release notes: none
larryliu0820
approved these changes
Aug 7, 2025
BujSet
force-pushed
the
zephyr_ci_models_test_more_models
branch
from
32857db to
561dd84
Compare
BujSet
force-pushed
the
zephyr_ci_models_test_more_models
branch
6 times, most recently
from
3980a1f to
d99348c
Compare
… build. Added in an if guard and reloading of these variables when that happens
BujSet
force-pushed
the
zephyr_ci_models_test_more_models
branch
from
d99348c to
b2a355e
Compare
agrima1304
pushed a commit
to agrima1304/executorch
that referenced
this pull request
Aug 26, 2025
### Summary Previously, only the example Add model was included in the matrix of models that the Zephyr CI job tests. The Add model isn't very representative of real-world models, and may give a false sense of security on the functionality of incorporating ExecuTorch with Zephyr. This PR adds the simple `Softmax` and `Mobilenet V2` models to the test matrix. While the `Softmax` model is like the `Add` model (a toy example), `Mobilenet V2` includes using an image from the `imagenet` validation set, and verifies that the top predicted label matches expectation (i.e. predict "Samoyed" as best label). All three of these tests show example of this flow can be extend further for other models. Thus this PR integrates these test to ensure compatibility between ExecuTorch and Zephyr is maintained. ### Test plan Verified that these models work with the Zephyr ecosystem manually in a separate docker image.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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.
Summary
Previously, only the example Add model was included in the matrix of models that the Zephyr CI job tests. The Add model isn't very representative of real-world models, and may give a false sense of security on the functionality of incorporating ExecuTorch with Zephyr. This PR adds the simple
SoftmaxandMobilenet V2models to the test matrix. While theSoftmaxmodel is like theAddmodel (a toy example),Mobilenet V2includes using an image from theimagenetvalidation set, and verifies that the top predicted label matches expectation (i.e. predict "Samoyed" as best label). All three of these tests show example of this flow can be extend further for other models. Thus this PR integrates these test to ensure compatibility between ExecuTorch and Zephyr is maintained.Test plan
Verified that these models work with the Zephyr ecosystem manually in a separate docker image.