-
Notifications
You must be signed in to change notification settings - Fork 795
Arm Backend: add .pte file visualization in Model Explorer #16290
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
Arm Backend: add .pte file visualization in Model Explorer #16290
Conversation
For the Ethos-U delegate, we need to handle intermediate .tosa artifacts. Invoke the PTE adapter API to do that. Signed-off-by: Tomás González <[email protected]>
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16290
Note: Links to docs will display an error until the docs builds have been completed. ❌ 3 New Failures, 7 Unrelated FailuresAs of commit 4de16b3 with merge base db895e9 ( 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
UNSTABLE - The following job is marked as unstable, possibly due to flakiness on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
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.
Pull request overview
This PR adds visualization support for PTE (PyTorch Export) files in Model Explorer for the Arm backend, complementing the existing TOSA visualization capability. Users can now choose between visualizing TOSA flatbuffer models or PTE models with their delegates through new command-line flags.
Key changes:
- Modified
run.shto add--visualize_pteand--visualize_tosaflags for choosing visualization format - Updated
visualize.pyto handle both PTE and TOSA visualization modes with appropriate adapter logic - Added
pte-adapter-model-explorerdependency for PTE visualization support
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 4 comments.
| File | Description |
|---|---|
| examples/arm/visualize.py | Refactored to support both PTE and TOSA visualization modes with new configuration functions and command-line argument handling |
| examples/arm/run.sh | Added flags for selecting visualization format (PTE or TOSA) and updated help text and logic accordingly |
| backends/arm/requirements-arm-ethos-u.txt | Added pte-adapter-model-explorer dependency for PTE visualization |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
|
@pytorchbot label ciflow/trunk |
|
To add these label(s) (ciflow/trunk) to the PR, please first approve the workflows that are awaiting approval (scroll to the bottom of this page). This helps ensure we don't trigger CI on this PR until it is actually authorized to do so. Please ping one of the reviewers if you do not have access to approve and run workflows. |
|
@pytorchbot label "partner: arm" |
|
@pytorchbot label "release notes: arm" |
|
To add the ciflow label This helps ensure we don't trigger CI on this PR until it is actually authorized to do so. Please ping one of the reviewers if you do not have access to approve and run workflows. |
Signed-off-by: Tomás González <[email protected]> Change-Id: Ic3e49022bbade1aa74590c06eeb0a06f8cef6199
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.
Pull request overview
Copilot reviewed 3 out of 3 changed files in this pull request and generated 5 comments.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
|
Known unrelated Arm fails Waiting on one more Arm test (and all other tests to finish) |
|
Oter fails are also unrelated |
Summary
Modify
examples/arm/run.shandexamples/arm/visualize.pyto be able to trigger visualization (pte or tosa) of the model.For the Ethos-U delegate, we need to pass down intermediate .tosa artifacts. Invoke the PTE adapter API to do that.
Test plan
I tested with
./examples/arm/run.sh --model_name=mv2 --model_explorer --visualize_pte./examples/arm/run.sh --model_name=mv2 --target="vgf" --model_explorer --visualize_pte./examples/arm/run.sh --model_name=mv2 --model_explorer --visualize_tosacc @freddan80 @per @zingo @oscarandersson8218 @digantdesai