Arm backend: Make composable_quantizer default

[AdrianLundell]

A few fixes needed:

• Add new ops added since initial upstream of composable_quantizer
• Add while-op quantize fix from 3be4546 to TosaQuantizerV2
• Add fixed_qparams fix from fb90480 to TosaQuantizerV2
• Update some tests to mirror new behaviours
• Update quanitzer_tutorial to not be WIP
• Remove hardsigmoid from FUSED_ACTIVATION_OPS
• Explicitly check that weights and biases are input args to conv/ linear ops. The assumption that wights and biases are the only parameters of networks does not hold for real models.

cc @digantdesai @freddan80 @per @zingo @oscarandersson8218 @mansnils @Sebastian-Larsson @robell @rascani

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19758

• 📄 Preview Python docs built from this PR

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

✅ No Failures

As of commit 130f60b with merge base e182e8b ():
💚 Looks good so far! There are no failures yet. 💚

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

[linux-foundation-easycla]

The committers listed above are authorized under a signed CLA.

• ✅ login: AdrianLundell / name: Adrian Lundell (4595733, c2a9306)

[Copilot]

Pull request overview

This PR switches the Arm backend’s TOSAQuantizer to use the composable quantizer implementation by default, and updates Arm quantization annotation/support logic plus tests/tutorial materials to match the new behaviors (including while-loop and fixed-qparams handling).

Changes:

• Make TOSAQuantizer default to use_composable_quantizer=True.
• Extend/update quantizer support + annotation behavior (e.g., while-loop shared-qspec handling, fixed-qparams input qspecs for trig ops, additional supported ops).
• Update Arm backend tests and the Arm quantizer tutorial notebook to reflect the new defaults/behaviors.

Reviewed changes

Copilot reviewed 10 out of 10 changed files in this pull request and generated 2 comments.

Show a summary per file

File	Description
examples/arm/quantizer_tutorial.ipynb	Removes WIP framing in the composable quantizer tutorial intro.
backends/arm/test/ops/test_while.py	Adds an INT while-loop test path forcing composable quantizer usage.
backends/arm/test/ops/test_transpose_conv2d.py	Updates tests to use TOSAQuantizationConfig for global config setup.
backends/arm/test/ops/test_to_copy.py	Simplifies redundant-cast xfail configuration shared between FP/INT.
backends/arm/test/misc/test_shared_qspecs.py	Updates golden expectations for shared-qspec annotation counts/qparams.
backends/arm/test/misc/test_quant_custom_meta.py	Adjusts test quantizer config (including set_io(None)) to match new behavior.
backends/arm/quantizer/quantizer_support.py	Updates supported/fused patterns (and adds more supported ops).
backends/arm/quantizer/quantization_config.py	Adds fixed-qparams input spec generation for specific trig ops under composable flow.
backends/arm/quantizer/arm_quantizer.py	Makes composable quantizer the default for TOSAQuantizer.
backends/arm/quantizer/arm_quantizer_utils.py	Tightens weight/bias identification and adds while-loop shared-qspec special-casing; extends shared-qspec op list.

---

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

[meta-codesync]

@rascani has imported this pull request. If you are a Meta employee, you can view this in D106381887.

[rascani]

Kicking off an internal test run.

[rascani]

It looks like the new quantizer breaks examples/models/llama/tests/test_export_llama_lib.py, because of asserts on quantizer.module_type_config, which is not implemented by the new quantizer. I think we should probably just remove those asserts in the tests unless you want to expose the module type config in the new quantizer.

https://github.com/pytorch/executorch/blob/main/examples/models/llama/tests/test_export_llama_lib.py#L121

[Copilot]

Pull request overview

Copilot reviewed 15 out of 15 changed files in this pull request and generated 4 comments.

[rascani]

Kicking off another internal run.

[digantdesai]

FYI @3l1 - not sure if you saw this.

[digantdesai]

From @rascani 's internal CI runs,

executorch/backends/arm/quantizer/arm_quantizer.py", line 522, in global_config
    raise NotImplementedError(
NotImplementedError: Composable quantizer does not allow setting global_config directly. Please use set_global() instead.

These should be forward fixed.

[rascani]

From @rascani 's internal CI runs,

executorch/backends/arm/quantizer/arm_quantizer.py", line 522, in global_config
    raise NotImplementedError(
NotImplementedError: Composable quantizer does not allow setting global_config directly. Please use set_global() instead.

These should be forward fixed.

I already have these fixed in D106539874. I'll land it ahead of time so the default switch can be a no-op.

[AdrianLundell]

@rascani Which setter-removal do you mean? I don't think setting the config from a dict has been the intended API, setting it using the setter functions should be intact.

[rascani]

@rascani Which setter-removal do you mean? I don't think setting the config from a dict has been the intended API, setting it using the setter functions should be intact.

We hit many of the NotImplementedError exceptions in this block:

executorch/backends/arm/quantizer/arm_quantizer.py

Lines 539 to 603 in e28ef13

	def global_config(self, value: Optional[QuantizationConfig]) -> None:
	if isinstance(self.quantizer, _TOSAQuantizerV1):
	self.quantizer.global_config = value
	else:
	raise NotImplementedError(
	"Composable quantizer does not allow setting global_config directly. Please use set_global() instead."
	)
	@property
	def io_config(self):
	if isinstance(self.quantizer, _TOSAQuantizerV1):
	return self.quantizer.io_config
	else:
	raise NotImplementedError(
	"Composable quantizer does not allow accessing io_config."
	)
	@io_config.setter
	def io_config(self, value: Optional[QuantizationConfig]) -> None:
	if isinstance(self.quantizer, _TOSAQuantizerV1):
	self.quantizer.io_config = value
	else:
	raise NotImplementedError(
	"Composable quantizer does not allow setting io_config directly. Please use set_io() instead."
	)
	@property
	def module_type_config(self):
	if isinstance(self.quantizer, _TOSAQuantizerV1):
	return self.quantizer.module_type_config
	else:
	raise NotImplementedError(
	"Composable quantizer does not allow accessing module_type_config."
	)
	@module_type_config.setter
	def module_type_config(
	self, value: Dict[Callable, Optional[QuantizationConfig]]
	) -> None:
	if isinstance(self.quantizer, _TOSAQuantizerV1):
	self.quantizer.module_type_config = value
	else:
	raise NotImplementedError(
	"Composable quantizer does not allow setting module_type_config directly. Please use set_module_type() instead."
	)
	@property
	def module_name_config(self):
	if isinstance(self.quantizer, _TOSAQuantizerV1):
	return getattr(self.quantizer, "module_name_config", {})
	else:
	raise NotImplementedError(
	"Composable quantizer does not allow accessing module_name_config."
	)
	@module_name_config.setter
	def module_name_config(
	self, value: Dict[str, Optional[QuantizationConfig]]
	) -> None:
	if isinstance(self.quantizer, _TOSAQuantizerV1):
	self.quantizer.module_name_config = value
	else:
	raise NotImplementedError(
	"Composable quantizer does not allow setting module_name_config directly. Please use set_module_name() instead."
	)

[AdrianLundell]

I would recommend replacing accessing e.g. module_name_config directly with using the official set_module_name setter API in that case, does that resolve the issue?

[AdrianLundell]

I realize we could also make a setter which takes the dict and calls set_module_name on all entries to have no breakage, would that help?

[Copilot]

Pull request overview

Copilot reviewed 12 out of 12 changed files in this pull request and generated 2 comments.

[AdrianLundell]

I had to take a break from this one, but now you should be able to set quantization specs from dicts as you are used to @rascani.

[AdrianLundell]

Look like the quantizers have diverged again, I will fix in a separate commit.

[digantdesai]

Still blocked on us, sorry.

[digantdesai]

Review automatically exported from Phabricator review in Meta.

[zingo]

Yeah!

[digantdesai]

Review automatically exported from Phabricator review in Meta.

sorry error on my part. Let me revert.

[AdrianLundell]

I see, when would you say this will be unblocked and can I make any updates to make it easier? @digantdesai

[rascani]

I see, when would you say this will be unblocked and can I make any updates to make it easier? @digantdesai

We had a bit of a race condition with an internal change. Barring no surprises, I am hoping to reland this today.

[rascani]

I see, when would you say this will be unblocked and can I make any updates to make it easier? @digantdesai

We had a bit of a race condition with an internal change. Barring no surprises, I am hoping to reland this today.

🤞 I think we should be good now.