NXP backend: added aten.mul support

[novak-vaclav]

Summary

adds support for aten.mul operator

Test plan

tests can be manually run using pytest -c /dev/null backends/nxp/tests/

cc @robert-kalmar @JakeStevens @digantdesai

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/15971

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

❌ 1 New Failure

As of commit b25bcdd with merge base 488d761 ():

NEW FAILURE - The following job has failed:

• pull / android / run-emulator (gh)
  Timeout waiting for emulator to boot.

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[novak-vaclav]

@pytorchbot label "release notes: nxp"

[Copilot]

Pull request overview

This PR adds support for the aten.mul (element-wise multiplication) operator to the NXP backend. The implementation includes quantization patterns, converter logic, and comprehensive test coverage.

Key changes:

• Implemented MulTensorConverter to convert aten.mul.Tensor operations to TensorFlow Lite IR
• Added MulTensorPattern quantization pattern with fixed quantization parameters
• Comprehensive test suite covering various input shapes, broadcasting scenarios, and edge cases

Reviewed changes

Copilot reviewed 8 out of 8 changed files in this pull request and generated 3 comments.

Show a summary per file

File	Description
backends/nxp/tests/models.py	Added three test model classes for mul operation testing
backends/nxp/tests/ir/converter/node_converter/test_mul_tensor_converter.py	Comprehensive test suite for mul tensor converter with multiple scenarios
backends/nxp/quantizer/patterns.py	Added MulTensorPattern class for quantization
backends/nxp/quantizer/neutron_quantizer.py	Registered MulTensorPattern in the quantizer
backends/nxp/neutron_partitioner.py	Registered MulTensorConverter in the partitioner
backends/nxp/backend/ir/converter/node_converters/ops_converters/mul_tensor_converter.py	Core converter implementation with target support validation
backends/nxp/backend/ir/converter/node_converters/ops_converters/__init__.py	Added MulTensorConverter to module exports
backends/nxp/backend/edge_program_converter.py	Registered converter in edge program converter

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Pull request overview

Copilot reviewed 8 out of 8 changed files in this pull request and generated 3 comments.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Pull request overview

Copilot reviewed 8 out of 8 changed files in this pull request and generated no new comments.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[MartinPavella]

I only have small suggestions for improvements. Please have a look at them.
Otherwise, well done 👍🏻

[MartinPavella]

A general tip:
We prefer to use rebase instead of merge to keep up with the base branch (main). It keeps the history nicer, and the lintrunner runs significantly faster.

[novak-vaclav]

A general tip: We prefer to use rebase instead of merge to keep up with the base branch (main). It keeps the history nicer, and the lintrunner runs significantly faster.

I had a discussion about it with @robert-kalmar and in the next PRs, I will try to keep a more structured commit history.

[novak-vaclav]

All issues found by @MartinPavella are fixed.

[MartinPavella]

Please update the branch to enable the tests.

[Copilot]

Pull request overview

Copilot reviewed 8 out of 8 changed files in this pull request and generated 3 comments.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Pull request overview

Copilot reviewed 8 out of 8 changed files in this pull request and generated no new comments.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[novak-vaclav]

@pytorchbot label "module: nxp"