NXP backend: Add dim order support to executorch_pipeline.py, add del… #17379
+46
−11
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/17379
Note: Links to docs will display an error until the docs builds have been completed. ❌ 2 New Failures, 2 PendingAs of commit 7daa71e with merge base b871398 ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
roman-janik-nxp
added
module: nxp
roman-janik-nxp
requested review from
MartinPavella,
StrycekSimon and
jirioc
meta-cla
bot
added
the
CLA Signed
MartinPavella
approved these changes
Feb 12, 2026
| dtype: torch.dtype = torch.float32 | ||
| dim_order: memory_format = torch.contiguous_format | ||
|
|
||
| def _convert_input_dim_order(example_input, input_spec): |
Collaborator
There was a problem hiding this comment.
Nit:
The name is misleading. Across our code-base, converting dim orders (node formats) means converting the formats to "equivalent" ones in the other framework (for example channels first -> channels last).
This function converts input data to specified dim order. Please consider a different name. (and type-hints wouldn't hurt)
roman-janik-nxp
force-pushed
the
feature/nxg11066/EIEX-712-Add-dim-order-support-to-pipeline
branch
from
143e923 to
6166623
Compare
…egate_to_npu switch
roman-janik-nxp
force-pushed
the
feature/nxg11066/EIEX-712-Add-dim-order-support-to-pipeline
branch
from
6166623 to
7daa71e
Compare
|
|
||
| def _convert_input_data_to_expected_dim_order( | ||
| example_input: tuple[torch.Tensor, ...], input_spec: tuple[ModelInputSpec, ...] | ||
| ): |
Collaborator
There was a problem hiding this comment.
Thanks for adding the type-hints, but you forgot to annotate the return type.
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.
…egate_to_npu switch
Summary
Adds support for dim-order feature to example inputs in the pipeline. Adds
delegate_to_npuswitch.Test plan
All NXP backend tests using executorch_pipeline.py.
cc @robert-kalmar @JakeStevens @digantdesai