Add 16A8W support and test for add operation #13653

Ninja91 · 2025-08-25T20:39:56Z

Stack from ghstack (oldest at bottom):

-> Add 16A8W support and test for add operation #13653

Add 16A8W quantization support and test for the add operation in ExecutorTorch ARM backend.

This follows the pattern established for linear operations, extending int16 support to add operations.

Changes:

Add INT16 dtype validation support in op_add.py
Add test_add_tensor_16a8w_tosa_INT test function
Enable test_add.py in test targets configuration

The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency.

Differential Revision: D80510463

Add 16A8W quantization support and test for the add operation in ExecutorTorch ARM backend. This follows the pattern established for linear operations, extending int16 support to add operations. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function - Enable test_add.py in test targets configuration The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency. Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463/) [ghstack-poisoned]

Add 16A8W quantization support and test for the add operation in ExecutorTorch ARM backend. This follows the pattern established for linear operations, extending int16 support to add operations. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function - Enable test_add.py in test targets configuration The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency. Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463/) ghstack-source-id: 305494940 Pull Request resolved: #13653

pytorch-bot · 2025-08-25T20:40:02Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/13653

📄 Preview Python docs built from this PR

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

❌ 4 New Failures

As of commit 2e94ad7 with merge base 9053089 ():

NEW FAILURES - The following jobs have failed:

Build documentation / build (buck2) / Build doc (gh)
At least one of the pre-conditions you specified did not hold
Propose to merge ghstack orig PRs to main / Try to create a PR with ghstack /orig branch (gh)
Process completed with exit code 1.
pull / unittest-arm-backend-with-no-fvp (test_pytest_models) / linux-job (gh)
backends/arm/test/models/stable_diffusion/test_T5EncoderModel.py::TestT5EncoderModel::test_T5EncoderModel_tosa_MI
pull / unittest-arm-backend-with-no-fvp (test_pytest_ops) / linux-job (gh)
RuntimeError: Command docker exec -t 167f5df21ba07ccf82352d21625792649cd5d4a5c429adbc906b07691eada078 /exec failed with exit code 1

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

facebook-github-bot · 2025-08-25T20:40:09Z

This pull request was exported from Phabricator. Differential Revision: D80510463

github-actions · 2025-08-25T20:45:30Z

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.

Add 16A8W quantization support and test for the add operation in ExecutorTorch ARM backend. This follows the pattern established for linear operations, extending int16 support to add operations. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function - Enable test_add.py in test targets configuration The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency. Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463/) [ghstack-poisoned]

Pull Request resolved: #13653 Add 16A8W quantization support and test for the add operation in ExecutorTorch ARM backend. This follows the pattern established for linear operations, extending int16 support to add operations. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function - Enable test_add.py in test targets configuration The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency. ghstack-source-id: 305600975 @exported-using-ghexport Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463/)

facebook-github-bot · 2025-08-26T04:16:39Z

This pull request was exported from Phabricator. Differential Revision: D80510463

backends/arm/test/ops/test_add.py

digantdesai

LGTM, mark xfail and we can land this.

Add 16A8W quantization support and test for the add operation in ExecutorTorch ARM backend. This follows the pattern established for linear operations, extending int16 support to add operations. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function - Enable test_add.py in test targets configuration The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency. Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463/) [ghstack-poisoned]

facebook-github-bot · 2025-08-26T23:37:29Z

This pull request was exported from Phabricator. Differential Revision: D80510463

Add 16A8W quantization support and test for the add operation in ExecutorTorch ARM backend. This follows the pattern established for linear operations, extending int16 support to add operations. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function - Enable test_add.py in test targets configuration The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency. Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463/) [ghstack-poisoned]

Pull Request resolved: #13653 Add 16A8W quantization support and test for the add operation in ExecutorTorch ARM backend. This follows the pattern established for linear operations, extending int16 support to add operations. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function - Enable test_add.py in test targets configuration The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency. ghstack-source-id: 305897355 @exported-using-ghexport Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463/)

facebook-github-bot · 2025-08-27T06:31:01Z

This pull request was exported from Phabricator. Differential Revision: D80510463

Ninja91 · 2025-08-29T05:48:34Z

CLosing this as I have updated PR here: #13789

Ninja91 requested a review from digantdesai as a code owner August 25, 2025 20:39

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 Aug 25, 2025

facebook-github-bot added the fb-exported label Aug 25, 2025

This was referenced Aug 26, 2025

Add 16A8W quantization configuration utility for ARM backend #13641

Merged

Add 16A8W linear ops support and test #13658

Merged

digantdesai reviewed Aug 26, 2025

View reviewed changes

backends/arm/test/ops/test_add.py Show resolved Hide resolved

digantdesai requested changes Aug 26, 2025

View reviewed changes

Ninja91 mentioned this pull request Aug 27, 2025

[Arm] Support INT16 ADD ops with TOSA reference model run #13730

Closed

Ninja91 closed this Aug 29, 2025

Ninja91 had a problem deploying to cherry-pick-bot August 29, 2025 05:48 — with GitHub Actions Failure

Ninja91 mentioned this pull request Aug 29, 2025

Arm backend: Add 16A8W support and test for add operation #13789

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Add 16A8W support and test for add operation #13653

Add 16A8W support and test for add operation #13653

Uh oh!

Ninja91 commented Aug 25, 2025 •

edited

Loading

Uh oh!

pytorch-bot bot commented Aug 25, 2025 •

edited

Loading

Uh oh!

facebook-github-bot commented Aug 25, 2025

Uh oh!

github-actions bot commented Aug 25, 2025

Uh oh!

facebook-github-bot commented Aug 26, 2025

Uh oh!

Uh oh!

digantdesai left a comment

Uh oh!

facebook-github-bot commented Aug 26, 2025

Uh oh!

facebook-github-bot commented Aug 27, 2025

Uh oh!

Ninja91 commented Aug 29, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Add 16A8W support and test for add operation #13653

Add 16A8W support and test for add operation #13653

Uh oh!

Conversation

Ninja91 commented Aug 25, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

pytorch-bot bot commented Aug 25, 2025 • 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/13653

❌ 4 New Failures

Uh oh!

facebook-github-bot commented Aug 25, 2025

Uh oh!

github-actions bot commented Aug 25, 2025

This PR needs a release notes: label

Uh oh!

facebook-github-bot commented Aug 26, 2025

Uh oh!

Uh oh!

digantdesai left a comment

Choose a reason for hiding this comment

Uh oh!

facebook-github-bot commented Aug 26, 2025

Uh oh!

facebook-github-bot commented Aug 27, 2025

Uh oh!

Ninja91 commented Aug 29, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Ninja91 commented Aug 25, 2025 •

edited

Loading

pytorch-bot bot commented Aug 25, 2025 •

edited

Loading

This PR needs a `release notes:` label