NXP backend: Catching the converter failures. #14117
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/14117
Note: Links to docs will display an error until the docs builds have been completed. ✅ You can merge normally! (6 Unrelated Failures)As of commit c3f5a69 with merge base 6ed10e5 ( 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
bot
added
the
CLA Signed
jirioc
added
ciflow/trunk
module: nxp
|
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. |
| @@ -3,11 +3,18 @@ | |||
| # This source code is licensed under the BSD-style license found in the | |||
There was a problem hiding this comment.
# Copyright 2024-2025 NXP
| @@ -52,6 +59,25 @@ def convert( | |||
| cctx.targetOpts = neutron_converter.getNeutronTarget(target) | |||
| # New switch since Neutron Converter SDK_25.06 | |||
| cctx.compilationOpts.minNumOpsPerGraph = 1 | |||
| model_converted = neutron_converter.convertModel(list(tflite_model), cctx) | |||
| # Don't merge `Transpose` operators, to avoid creating unsupported permutations. | |||
| cctx.compilationOpts.excludeGraphPasses = "MergeTranspose" | |||
There was a problem hiding this comment.
This should probably not be included, as proper permute_copy support has not been up-streamed yet.
| import pkgutil | ||
|
|
||
| from executorch.backends.nxp.backend.ir.converter.node_converter import Target | ||
|
|
||
|
|
||
| def convert_unsafe(neutron_converter, tflite_model, cctx, queue): |
There was a problem hiding this comment.
A documentation comment would be useful here.
There was a problem hiding this comment.
@jirioc, can you please add it?
StrycekSimon
force-pushed
the
upstream/main-nxp/EIEX-532-upstream-converter-failure-catching
branch
from
62ab20c to
fce6017
Compare
jirioc
force-pushed
the
upstream/main-nxp/EIEX-532-upstream-converter-failure-catching
branch
from
fce6017 to
ee901ae
Compare
jirioc
force-pushed
the
upstream/main-nxp/EIEX-532-upstream-converter-failure-catching
branch
from
ee901ae to
c3f5a69
Compare
roman-janik-nxp
approved these changes
Sep 11, 2025
|
Seems like the failed tests are unrelated to this PR. |
robert-kalmar
approved these changes
Sep 12, 2025
robert-kalmar
deleted the
upstream/main-nxp/EIEX-532-upstream-converter-failure-catching
branch
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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
This feature makes the flow robust against Neutron converter crash/exit. Especially useful for running unit tests.
Test plan
When the nxp unit tests pass, the Neutron converter is properly invoked. No need for extra testing.
cc @digantdesai @JakeStevens @robert-kalmar