NXP backend: added support for aten.bmm

[novak-vaclav]

Summary

adds support for aten.bmm operator

Test plan

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

cc @robert-kalmar @JakeStevens @digantdesai @roman-janik-nxp @MartinPavella @StrycekSimon @jirioc

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17670

• 📄 Preview Python docs built from this PR

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

❌ 6 New Failures

As of commit 5035fec with merge base 746db5f ():

NEW FAILURES - The following jobs have failed:

• Lint / lintrunner / linux-job (gh)
  >>> Lint for backends/nxp/tests/ir/converter/node_converter/test_bmm_converter.py:
• pull / test-mediatek-models-linux / linux-job (gh)
  RuntimeError: Command docker exec -t dc61e337aa4530434354e2586fdc58b48a564e606a002f7006ecdaa6983dea2d /exec failed with exit code 2
• pull / test-openvino-linux / linux-job (gh)
  RuntimeError: Command docker exec -t 8fbb5fa630103920e2f1ccaa0fa1191893b26d8824b49a765de2f02886cc9bdf /exec failed with exit code 1
• pull / test-samsung-models-linux / linux-job (gh)
  RuntimeError: Command docker exec -t 966971b892b20a6dbb948863e47963f9037575d8756d24a01f41d53c602a78c7 /exec failed with exit code 1
• pull / test-samsung-quantmodels-linux / linux-job (gh)
  RuntimeError: Command docker exec -t cfa665a1a115b541d2be25b66bc2b5904f504a27653d059dec0ce7bf1c9779ea /exec failed with exit code 1
• pull / unittest-arm-backend-with-no-deps (test_pytest_ops_tosa) / linux-job (gh)
  RuntimeError: Command docker exec -t 2a988e152ddc254b03fd6255037f33d288c403c504182bf778d3cde309664c64 /exec failed with exit code 1

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

[novak-vaclav]

@pytorchbot label "release notes: nxp"

[novak-vaclav]

@pytorchbot label "module: nxp"

[novak-vaclav]

In the last force-push, I just added the brief operator support description to op-support.csv

[Copilot]

Pull request overview

Adds NXP backend support for the aten.bmm operator by introducing a new IR converter and quantization pattern, updating delegation maps, and adding basic converter tests and documentation.

Changes:

• Register aten.bmm for delegation and conversion (partitioner + EdgeProgram IR converter).
• Add BMMConverter (TFLite BatchMatMul) and BMMPattern for quantization annotation.
• Add bmm test models + a new node-converter test module; update NXP op-support docs.

Reviewed changes

Copilot reviewed 9 out of 9 changed files in this pull request and generated 3 comments.

Show a summary per file

File	Description
docs/source/backends/nxp/op-support.csv	Documents aten.bmm.default support and target constraints.
backends/nxp/tests/models.py	Adds simple modules exercising torch.bmm (including a conv→bmm path).
backends/nxp/tests/ir/converter/node_converter/test_bmm_converter.py	Adds conversion/delegation tests for bmm.
backends/nxp/quantizer/patterns.py	Introduces BMMPattern to annotate bmm quantization behavior.
backends/nxp/quantizer/neutron_quantizer.py	Registers BMMPattern in the quantizer op list.
backends/nxp/neutron_partitioner.py	Adds aten.bmm → BMMConverter mapping for partitioning.
backends/nxp/backend/ir/converter/node_converters/ops_converters/bmm_converter.py	Implements aten.bmm → TFLite BatchMatMul conversion.
backends/nxp/backend/ir/converter/node_converters/ops_converters/init.py	Exports BMMConverter.
backends/nxp/backend/edge_program_converter.py	Adds aten.bmm → BMMConverter mapping for program conversion.

---

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