-
Notifications
You must be signed in to change notification settings - Fork 668
Summary: MCU Tests: Add two basic qadd , qlinear qdq tests #14440
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.
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
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14440
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit 5cc83fe with merge base a548635 ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This PR needs a
|
"qops": QuantOpTest, | ||
"softmax": SoftmaxModule, | ||
"MultipleOutputsModule": MultipleOutputsModule, | ||
"qlinear": QuantLinearTest, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Add a TODO for more tests, link the tester RFC thing from @AdrianLundell here?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
done
examples/arm/aot_arm_compiler.py
Outdated
def __init__(self): | ||
super().__init__() | ||
# Define a simple linear layer | ||
self.linear = torch.nn.Linear(64, 32) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
let's use prime numbers instead of powers of two..
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
done
-m "$model" \ | ||
--target="$ETHOS_TARGET" \ | ||
--quantize \ | ||
--enable_qdq_fusion_pass \ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
always enable?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Few internal CI tests were failing, I will fix them first and then enable
- Enable on CI for consistent signals - Note that this is interim solution until a proper MCU testing standalone pipeline is ready Test Plan: - examples/arm/run_mcu_models_fvp.sh --target=cortex-m55 --models=qadd,qlinear ════════════════════════════════════════════════════════════════ 🏁 MCU MODEL VALIDATION SUMMARY - TARGET: cortex-m55 ════════════════════════════════════════════════════════════════ qadd : ✅ Passed qlinear : ✅ Passed Reviewers: Subscribers: Tasks: Tags:
Test Plan:
qadd : ✅ Passed
qlinear : ✅ Passed
Reviewers:
Subscribers:
Tasks:
Tags:
Summary
[PLEASE REMOVE] See CONTRIBUTING.md's Pull Requests for ExecuTorch PR guidelines.
[PLEASE REMOVE] If this PR closes an issue, please add a
Fixes #<issue-id>
line.[PLEASE REMOVE] If this PR introduces a fix or feature that should be the upcoming release notes, please add a "Release notes: " label. For a list of available release notes labels, check out CONTRIBUTING.md's Pull Requests.
Test plan
[PLEASE REMOVE] How did you test this PR? Please write down any manual commands you used and note down tests that you have written if applicable.