Arm backend: Make composable_quantizer default by AdrianLundell · Pull Request #19758 · pytorch/executorch

AdrianLundell · 2026-05-25T15:05:37Z

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

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 hardswish 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. Signed-off-by: Adrian Lundell <adrian.lundell@arm.com> Change-Id: Ifa127a73d4db45cd2d3461101f97c0cf852bf7bf

pytorch-bot · 2026-05-25T15:05:42Z

🔗 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.

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

/easycla is not responding

❌ 4 New Failures, 4 Unrelated Failures

As of commit 6c4194e with merge base 77df9b7 ():

NEW FAILURES - The following jobs have failed:

pull / android / build-android (gh)
Process completed with exit code 9.
pull / unittest / linux / linux-job (gh)
RuntimeError: Command docker exec -t 2ac9af9e3db4ce5a1ec5435ec961991180200f65ce67dffe257b330be6e97e14 /exec failed with exit code 1
pull / unittest-editable / linux / linux-job (gh)
RuntimeError: Command docker exec -t 965b148a49dbb915a3a2543fac59760730952d1ef5bf4f3e4a7254d0e071ca66 /exec failed with exit code 1
trunk / unittest-release / linux / linux-job (gh)
RuntimeError: Command docker exec -t a982faa824b6d0ec17f9d71eb8fb36d1aaf138e3b8577e6e410a34404820c971 /exec failed with exit code 1

BROKEN TRUNK - The following jobs failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

pull / test-static-llama-qnn-linux (stories_110m) / linux-job (gh) (trunk failure)
test_llama_stories_110m
pull / unittest / macos / macos-job (gh) (trunk failure)
##[error]The operation was canceled.
pull / unittest-editable / macos / macos-job (gh) (trunk failure)
##[error]The operation was canceled.
trunk / unittest-release / macos / macos-job (gh) (trunk failure)
##[error]The operation was canceled.

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

linux-foundation-easycla · 2026-05-25T15:05:45Z

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.

Signed-off-by: Adrian Lundell <adrian.lundell@arm.com> Change-Id: I75e207d010b2bdc9abc86023153c86d2c96af3fd

meta-codesync · 2026-05-26T15:48:16Z

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

rascani · 2026-05-26T15:49:33Z

Kicking off an internal test run.

rascani · 2026-05-26T23:20:25Z

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

…tream/change-1253855 Change-Id: I86bc8025e41175a796fa0ff7aabc9847b1de923a

These configs does not exist in the new quantizer, so checking it does not make sense anymore. Signed-off-by: Adrian Lundell <adrian.lundell@arm.com> Change-Id: Ic6c0b303466010be59e9c9c37fb179938c412a16

Copilot

Pull request overview

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

+        elif node.target in _fixed_input_qspec_ops:
+
+            input_act_qspec = super().get_input_act_qspec(node, input_node)
+            num_bits = torch.iinfo(input_act_qspec.dtype).bits
+            qparams = _fixed_input_qspec_ops[node.target][num_bits]
+            return FixedQParamsQuantizationSpec(
+                dtype=input_act_qspec.dtype,
+                scale=qparams.scale,
+                zero_point=qparams.zero_point,
+                quant_min=input_act_qspec.quant_min,
+                quant_max=input_act_qspec.quant_max,
+                qscheme=input_act_qspec.qscheme,
+                is_dynamic=input_act_qspec.is_dynamic,
+            )


Signed-off-by: Adrian Lundell <adrian.lundell@arm.com> Change-Id: I7760780d4f06e300f17575e7c6cb34c6dfdae64c

rascani · 2026-05-27T15:15:35Z

Kicking off another internal run.

digantdesai · 2026-05-27T22:54:28Z

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

digantdesai · 2026-05-27T23:03:37Z

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 · 2026-05-27T23:21:17Z

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.

Signed-off-by: Adrian Lundell <adrian.lundell@arm.com> Change-Id: Ib6fefa3ba308d955b46e23095633f54df8ed3bf0

AdrianLundell requested review from 3l1 and Copilot May 25, 2026 15:05

AdrianLundell requested a review from digantdesai as a code owner May 25, 2026 15:05

AdrianLundell added help wanted Extra attention is needed partner: arm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Arm ciflow/trunk release notes: arm Changes to the ARM backend delegate labels May 25, 2026

meta-cla Bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label May 25, 2026

github-actions Bot added the module: arm Issues related to arm backend label May 25, 2026

Copilot started reviewing on behalf of AdrianLundell May 25, 2026 15:06 View session

Copilot AI reviewed May 25, 2026

View reviewed changes

Comment thread backends/arm/quantizer/arm_quantizer.py

Comment thread backends/arm/quantizer/quantizer_support.py

Make vgf/ethosu-quantizers composable by default

c2a9306

Signed-off-by: Adrian Lundell <adrian.lundell@arm.com> Change-Id: I75e207d010b2bdc9abc86023153c86d2c96af3fd

AdrianLundell requested a review from mergennachin as a code owner May 26, 2026 12:16

AdrianLundell added 2 commits May 27, 2026 10:25

Merge branch 'main' of https://github.com/pytorch/executorch into ups…

af8056f

…tream/change-1253855 Change-Id: I86bc8025e41175a796fa0ff7aabc9847b1de923a

Remove quanitzer config asserts from test_export_llama_lib.py

098d79b

These configs does not exist in the new quantizer, so checking it does not make sense anymore. Signed-off-by: Adrian Lundell <adrian.lundell@arm.com> Change-Id: Ic6c0b303466010be59e9c9c37fb179938c412a16

Copilot AI review requested due to automatic review settings May 27, 2026 08:45

Copilot started reviewing on behalf of AdrianLundell May 27, 2026 08:45 View session

Copilot AI reviewed May 27, 2026

View reviewed changes

Arm backend: Fix review comments

155b4df

Signed-off-by: Adrian Lundell <adrian.lundell@arm.com> Change-Id: I7760780d4f06e300f17575e7c6cb34c6dfdae64c

Add new ops to test_portable_int8

6c4194e

Signed-off-by: Adrian Lundell <adrian.lundell@arm.com> Change-Id: Ib6fefa3ba308d955b46e23095633f54df8ed3bf0

AdrianLundell requested a review from rascani as a code owner May 28, 2026 07:58

Conversation

AdrianLundell commented May 25, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

pytorch-bot Bot commented May 25, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🔗 Helpful Links

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

❗ 1 Active SEVs

❌ 4 New Failures, 4 Unrelated Failures

Uh oh!

linux-foundation-easycla Bot commented May 25, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Uh oh!

Uh oh!

meta-codesync Bot commented May 26, 2026

Uh oh!

rascani commented May 26, 2026

Uh oh!

rascani commented May 26, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

Uh oh!

Uh oh!

rascani commented May 27, 2026

Uh oh!

digantdesai commented May 27, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

digantdesai commented May 27, 2026

Uh oh!

rascani commented May 27, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

AdrianLundell commented May 25, 2026 •

edited

Loading

pytorch-bot Bot commented May 25, 2026 •

edited

Loading

linux-foundation-easycla Bot commented May 25, 2026 •

edited

Loading

digantdesai commented May 27, 2026 •

edited

Loading