Cortex-M Backend: Add tiny model tests for nn.Modules, nn.functional,…

[psiddh]

… and torch patterns

Add 21 new test cases across 3 files that exercise the Cortex-M quantizer and pass manager on small composite models. These mirror the Arm backend's test_nn_modules/test_nn_functional/test_torch_functions pattern but target the Cortex-M pipeline.

Tests cover: ConvBnReLU, LinearReLU, ConvTranspose2d, AdaptiveAvgPool2d, MaxPool2d, AvgPool2d, Softmax, Hardswish, Hardsigmoid, depthwise separable conv, inverted residual blocks (MobileNet-style), and multi-op functional compositions.

All tests use test_dialect() which runs quantize→export→to_edge→ run_passes→compare_outputs entirely on the host (no FVP needed).

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18297

• 📄 Preview Python docs built from this PR

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

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

[github-actions]

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

[Copilot]

Pull request overview

Adds new Cortex-M backend model-level test suites to exercise common composite patterns (torch op compositions, nn.Module building blocks, and torch.nn.functional usage) through the Cortex-M quantizer + pass pipeline.

Changes:

• Add composite “torch function pattern” models (mul/add, transpose+linear, conv chains, depthwise/inverted residual, linear+softmax).
• Add nn.Module-focused coverage (conv/bn/relu, pooling, conv-transpose, hardswish/sigmoid, softmax) with an explicit xfail.
• Add nn.functional-pattern coverage (conv+activation+pooling, pad, linear+bn, hardtanh).

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 5 comments.

File	Description
backends/cortex_m/test/models/test_torch_functions.py	New composite torch-op pattern tests for Cortex-M dialect pipeline
backends/cortex_m/test/models/test_nn_modules.py	New nn.Module composite tests + one documented xfail
backends/cortex_m/test/models/test_nn_functional.py	New functional-pattern composite tests for Cortex-M dialect pipeline

---

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

[Copilot]

Pull request overview

Adds Cortex‑M backend model-level test coverage for common torch composite patterns, nn.Module compositions, and torch.nn.functional usage by introducing three new pytest suites that run through the Cortex‑M quantizer and pass pipeline.

Changes:

• Add composite “torch function” pattern tests (arithmetic fusion, transpose+linear, conv blocks, MobileNet-style blocks, softmax).
• Add nn.Module composition tests (conv/bn/relu, pooling, activations, softmax, conv transpose, and an xfailed fusion case).
• Add torch.nn.functional-oriented tests (pad, activations, pooling, linear+BN composition).

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 7 comments.

File	Description
backends/cortex_m/test/models/test_torch_functions.py	New composite-pattern tests driven by CortexMTester.test_dialect
backends/cortex_m/test/models/test_nn_modules.py	New nn.Module composition tests with an explicit xfail for unsupported fusion
backends/cortex_m/test/models/test_nn_functional.py	New functional-style op composition tests (pad/activations/pooling/linear+BN)

---

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