Adding Test For CadenceWith16BitLinearActivationsQuantizer

[RahulC7]

Summary:
We test the CadenceWith16BitLinearActivationQuantizer.

We use the graph builder to build the graph with metadata(that's needed for quantizer.annotate to recognize the nodes), and we ensure that the quantization params are as expected.

Reviewed By: hsharma35

Differential Revision: D88054651

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16097

• 📄 Preview Python docs built from this PR

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

✅ You can merge normally! (1 Unrelated Failure)

As of commit 2085907 with merge base 3a76a8b ():

UNSTABLE - The following job is marked as unstable, possibly due to flakiness on trunk:

• pull / android / run-emulator (gh) (#16137)
  Timeout waiting for emulator to boot.

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

[meta-codesync]

@RahulC7 has exported this pull request. If you are a Meta employee, you can view the originating Diff in D88054651.

[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

This PR adds comprehensive unit tests for the CadenceWith16BitLinearActivationsQuantizer and CadenceWith16BitMatmulActivationsQuantizer classes. The tests verify that these quantizers correctly annotate graph nodes with 16-bit quantization specifications (INT16 for activations, INT8 for weights).

Key Changes:

• Adds a new test class QuantizerAnnotationTest with helper methods to build test graphs
• Tests 16-bit quantizer annotations for both matmul and linear operations
• Updates TARGETS file with necessary dependencies for the new tests

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

File	Description
backends/cadence/aot/tests/test_quantizer_ops.py	Adds QuantizerAnnotationTest class with tests for 16-bit quantizer annotations on matmul and linear operations
backends/cadence/aot/TARGETS	Adds dependencies for graph_builder, pass_base, and torchao modules

---

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

[Copilot]

The test should verify that all inputs in input_qspec_map are expected. Currently, if an unexpected input node appears that doesn't match linear_node.args[0] or linear_node.args[1], the test will silently pass without checking its qspec. Consider adding an else clause with a self.fail() to catch unexpected inputs:

for input_node, input_qspec in annotation.input_qspec_map.items():
    if input_node == linear_node.args[0]:
        # Activation input - should be INT16
        self.assertEqual(input_qspec, qconfig_A16.input_activation)
    elif input_node == linear_node.args[1]:
        # Weight - should be INT8
        self.assertEqual(input_qspec, qconfig_A16.weight)
    else:
        self.fail(f"Unexpected input node in input_qspec_map: {input_node}")

Suggested change

	else:
	self.fail(f"Unexpected input node in input_qspec_map: {input_node}")

[Copilot]

Pull request overview

Copilot reviewed 2 out of 2 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.