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

Ninja91 · 2025-08-29T04:20:09Z

Stack from ghstack (oldest at bottom):

Add 16A8W quantization support and comprehensive tests for the add operation in ExecutorTorch ARM backend targeting Ethos U55 and U85 NPUs.

This follows the pattern established for linear operations, extending int16 support to add operations with hardware-specific testing.

Changes:

Add INT16 dtype validation support in op_add.py
Add test_add_tensor_16a8w_tosa_INT test function with U55/U85 pipeline support
Add U55 and U85 specific 16A8W tests with proper xfail decorators
Fix U55/U85 test parameter usage (remove unsupported tosa_extensions, clean quantizer function calls)
Update xfail reasons to consistent 'Vela compilation fails with Invalid arguments' pattern

Differential Revision: D80510463

cc @digantdesai @freddan80 @per @zingo @oscarandersson8218

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]

pytorch-bot · 2025-08-29T04:20:13Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/13789

📄 Preview Python docs built from this PR

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

❌ 3 New Failures, 1 Cancelled Job

As of commit 3dbf93f with merge base 1a7441f ():

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
trunk / test-llama-runner-mac (fp32, coreml) / macos-job (gh)
RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1
trunk / test-models-macos-coreml (dl3) / macos-job (gh)
AttributeError: partially initialized module 'torchvision' has no attribute 'extension' (most likely due to a circular import)

CANCELLED JOB - The following job was cancelled. Please retry:

trunk / test-models-macos-cpu (mv3, xnnpack-quantization-delegation) / macos-job (gh)
##[error]The operation was canceled.

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

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: 305897355 Pull Request resolved: #13789

facebook-github-bot · 2025-08-29T04:20:20Z

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: #13789 Add 16A8W quantization support and comprehensive tests for the add operation in ExecutorTorch ARM backend targeting Ethos U55 and U85 NPUs. This follows the pattern established for linear operations, extending int16 support to add operations with hardware-specific testing. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function with U55/U85 pipeline support - Add U55 and U85 specific 16A8W tests with proper xfail decorators - Fix U55/U85 test parameter usage (remove unsupported tosa_extensions, clean quantizer function calls) - Update xfail reasons to consistent 'Vela compilation fails with Invalid arguments' pattern - Remove redundant u55_config parameter from get_symmetric_a16w8_add_quantizer function - Enable test_add.py in test targets configuration for both fbcode and xplat The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency on ARM Ethos NPUs. ghstack-source-id: 306430209 ghstack-source-id: 306430209 @exported-using-ghexport Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463/)

facebook-github-bot · 2025-08-29T05:11:08Z

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

Add 16A8W quantization support and comprehensive tests for the add operation in ExecutorTorch ARM backend targeting Ethos U55 and U85 NPUs. This follows the pattern established for linear operations, extending int16 support to add operations with hardware-specific testing. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function with U55/U85 pipeline support - Add U55 and U85 specific 16A8W tests with proper xfail decorators - Fix U55/U85 test parameter usage (remove unsupported tosa_extensions, clean quantizer function calls) - Update xfail reasons to consistent 'Vela compilation fails with Invalid arguments' pattern exported-using-ghexport Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463/) Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463) [ghstack-poisoned]

Pull Request resolved: #13789 Add 16A8W quantization support and comprehensive tests for the add operation in ExecutorTorch ARM backend targeting Ethos U55 and U85 NPUs. This follows the pattern established for linear operations, extending int16 support to add operations with hardware-specific testing. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function with U55/U85 pipeline support - Add U55 and U85 specific 16A8W tests with proper xfail decorators - Fix U55/U85 test parameter usage (remove unsupported tosa_extensions, clean quantizer function calls) - Update xfail reasons to consistent 'Vela compilation fails with Invalid arguments' pattern ghstack-source-id: 306430209 ghstack-source-id: 306430209 @exported-using-ghexport Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463/)

facebook-github-bot · 2025-08-29T05:18:25Z

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

Add 16A8W quantization support and comprehensive tests for the add operation in ExecutorTorch ARM backend targeting Ethos U55 and U85 NPUs. This follows the pattern established for linear operations, extending int16 support to add operations with hardware-specific testing. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function with U55/U85 pipeline support - Add U55 and U85 specific 16A8W tests with proper xfail decorators - Fix U55/U85 test parameter usage (remove unsupported tosa_extensions, clean quantizer function calls) - Update xfail reasons to consistent 'Vela compilation fails with Invalid arguments' pattern Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463) [ghstack-poisoned]

Pull Request resolved: #13789 Add 16A8W quantization support and comprehensive tests for the add operation in ExecutorTorch ARM backend targeting Ethos U55 and U85 NPUs. This follows the pattern established for linear operations, extending int16 support to add operations with hardware-specific testing. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function with U55/U85 pipeline support - Add U55 and U85 specific 16A8W tests with proper xfail decorators - Fix U55/U85 test parameter usage (remove unsupported tosa_extensions, clean quantizer function calls) - Update xfail reasons to consistent 'Vela compilation fails with Invalid arguments' pattern ghstack-source-id: 306430970 ghstack-source-id: 306430970 @exported-using-ghexport Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463/)

facebook-github-bot · 2025-08-29T05:43:18Z

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

Ninja91 · 2025-08-29T05:48:54Z

Closed #13653 as it's covered in this PR.

Pull Request resolved: #13789 Add 16A8W quantization support and comprehensive tests for the add operation in ExecutorTorch ARM backend targeting Ethos U55 and U85 NPUs. This follows the pattern established for linear operations, extending int16 support to add operations with hardware-specific testing. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function with U55/U85 pipeline support - Add U55 and U85 specific 16A8W tests with proper xfail decorators - Fix U55/U85 test parameter usage (remove unsupported tosa_extensions, clean quantizer function calls) - Update xfail reasons to consistent 'Vela compilation fails with Invalid arguments' pattern ghstack-source-id: 306434516 ghstack-source-id: 306434516 @exported-using-ghexport Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463/)

facebook-github-bot · 2025-09-04T01:19:52Z

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

Add 16A8W quantization support and comprehensive tests for the add operation in ExecutorTorch ARM backend targeting Ethos U55 and U85 NPUs. This follows the pattern established for linear operations, extending int16 support to add operations with hardware-specific testing. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function with U55/U85 pipeline support - Add U55 and U85 specific 16A8W tests with proper xfail decorators - Fix U55/U85 test parameter usage (remove unsupported tosa_extensions, clean quantizer function calls) - Update xfail reasons to consistent 'Vela compilation fails with Invalid arguments' pattern Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463) cc digantdesai freddan80 per zingo oscarandersson8218 [ghstack-poisoned]

facebook-github-bot · 2025-09-04T14:49:08Z

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

Add 16A8W quantization support and comprehensive tests for the add operation in ExecutorTorch ARM backend targeting Ethos U55 and U85 NPUs. This follows the pattern established for linear operations, extending int16 support to add operations with hardware-specific testing. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function with U55/U85 pipeline support - Add U55 and U85 specific 16A8W tests with proper xfail decorators - Fix U55/U85 test parameter usage (remove unsupported tosa_extensions, clean quantizer function calls) - Update xfail reasons to consistent 'Vela compilation fails with Invalid arguments' pattern Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463) cc digantdesai freddan80 per zingo oscarandersson8218 [ghstack-poisoned]

Pull Request resolved: #13789 Add 16A8W quantization support and comprehensive tests for the add operation in ExecutorTorch ARM backend targeting Ethos U55 and U85 NPUs. This follows the pattern established for linear operations, extending int16 support to add operations with hardware-specific testing. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function with U55/U85 pipeline support - Add U55 and U85 specific 16A8W tests with proper xfail decorators - Fix U55/U85 test parameter usage (remove unsupported tosa_extensions, clean quantizer function calls) - Update xfail reasons to consistent 'Vela compilation fails with Invalid arguments' pattern ghstack-source-id: 307540287 ghstack-source-id: 307540287 @exported-using-ghexport Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463/)

facebook-github-bot · 2025-09-04T15:56:12Z

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

Add 16A8W quantization support and comprehensive tests for the add operation in ExecutorTorch ARM backend targeting Ethos U55 and U85 NPUs. This follows the pattern established for linear operations, extending int16 support to add operations with hardware-specific testing. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function with U55/U85 pipeline support - Add U55 and U85 specific 16A8W tests with proper xfail decorators - Fix U55/U85 test parameter usage (remove unsupported tosa_extensions, clean quantizer function calls) - Update xfail reasons to consistent 'Vela compilation fails with Invalid arguments' pattern Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463) cc digantdesai freddan80 per zingo oscarandersson8218 [ghstack-poisoned]

facebook-github-bot · 2025-09-04T23:55:59Z

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

Add 16A8W quantization support and comprehensive tests for the add operation in ExecutorTorch ARM backend targeting Ethos U55 and U85 NPUs. This follows the pattern established for linear operations, extending int16 support to add operations with hardware-specific testing. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function with U55/U85 pipeline support - Add U55 and U85 specific 16A8W tests with proper xfail decorators - Fix U55/U85 test parameter usage (remove unsupported tosa_extensions, clean quantizer function calls) - Update xfail reasons to consistent 'Vela compilation fails with Invalid arguments' pattern Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463) cc digantdesai freddan80 per zingo oscarandersson8218 [ghstack-poisoned]

facebook-github-bot · 2025-09-05T00:16:28Z

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

Add 16A8W quantization support and comprehensive tests for the add operation in ExecutorTorch ARM backend targeting Ethos U55 and U85 NPUs. This follows the pattern established for linear operations, extending int16 support to add operations with hardware-specific testing. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function with U55/U85 pipeline support - Add U55 and U85 specific 16A8W tests with proper xfail decorators - Fix U55/U85 test parameter usage (remove unsupported tosa_extensions, clean quantizer function calls) - Update xfail reasons to consistent 'Vela compilation fails with Invalid arguments' pattern Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463) cc digantdesai freddan80 per zingo oscarandersson8218 [ghstack-poisoned]

Pull Request resolved: #13789 Add 16A8W quantization support and comprehensive tests for the add operation in ExecutorTorch ARM backend targeting Ethos U55 and U85 NPUs. This follows the pattern established for linear operations, extending int16 support to add operations with hardware-specific testing. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function with U55/U85 pipeline support - Add U55 and U85 specific 16A8W tests with proper xfail decorators - Fix U55/U85 test parameter usage (remove unsupported tosa_extensions, clean quantizer function calls) - Update xfail reasons to consistent 'Vela compilation fails with Invalid arguments' pattern ghstack-source-id: 308024224 ghstack-source-id: 308024224 @exported-using-ghexport Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463/)

facebook-github-bot · 2025-09-06T17:37:33Z

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

Add 16A8W quantization support and comprehensive tests for the add operation in ExecutorTorch ARM backend targeting Ethos U55 and U85 NPUs. This follows the pattern established for linear operations, extending int16 support to add operations with hardware-specific testing. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function with U55/U85 pipeline support - Add U55 and U85 specific 16A8W tests with proper xfail decorators - Fix U55/U85 test parameter usage (remove unsupported tosa_extensions, clean quantizer function calls) - Update xfail reasons to consistent 'Vela compilation fails with Invalid arguments' pattern Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463) cc digantdesai freddan80 per zingo oscarandersson8218 [ghstack-poisoned]

Pull Request resolved: #13789 Add 16A8W quantization support and comprehensive tests for the add operation in ExecutorTorch ARM backend targeting Ethos U55 and U85 NPUs. This follows the pattern established for linear operations, extending int16 support to add operations with hardware-specific testing. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function with U55/U85 pipeline support - Add U55 and U85 specific 16A8W tests with proper xfail decorators - Fix U55/U85 test parameter usage (remove unsupported tosa_extensions, clean quantizer function calls) - Update xfail reasons to consistent 'Vela compilation fails with Invalid arguments' pattern ghstack-source-id: 308046738 ghstack-source-id: 308046738 @exported-using-ghexport @bypass-github-pytorch-ci-checks Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463/)

facebook-github-bot · 2025-09-07T01:39:07Z

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

Add 16A8W quantization support and comprehensive tests for the add operation in ExecutorTorch ARM backend targeting Ethos U55 and U85 NPUs. This follows the pattern established for linear operations, extending int16 support to add operations with hardware-specific testing. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function with U55/U85 pipeline support - Add U55 and U85 specific 16A8W tests with proper xfail decorators - Fix U55/U85 test parameter usage (remove unsupported tosa_extensions, clean quantizer function calls) - Update xfail reasons to consistent 'Vela compilation fails with Invalid arguments' pattern Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463) cc digantdesai freddan80 per zingo oscarandersson8218 [ghstack-poisoned]

Pull Request resolved: #13789 Add 16A8W quantization support and comprehensive tests for the add operation in ExecutorTorch ARM backend targeting Ethos U55 and U85 NPUs. This follows the pattern established for linear operations, extending int16 support to add operations with hardware-specific testing. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function with U55/U85 pipeline support - Add U55 and U85 specific 16A8W tests with proper xfail decorators - Fix U55/U85 test parameter usage (remove unsupported tosa_extensions, clean quantizer function calls) - Update xfail reasons to consistent 'Vela compilation fails with Invalid arguments' pattern ghstack-source-id: 308052889 ghstack-source-id: 308052889 @exported-using-ghexport @bypass-github-pytorch-ci-checks Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463/)

facebook-github-bot · 2025-09-07T03:38:22Z

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

Add 16A8W quantization support and comprehensive tests for the add operation in ExecutorTorch ARM backend targeting Ethos U55 and U85 NPUs. This follows the pattern established for linear operations, extending int16 support to add operations with hardware-specific testing. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function with U55/U85 pipeline support - Add U55 and U85 specific 16A8W tests with proper xfail decorators - Fix U55/U85 test parameter usage (remove unsupported tosa_extensions, clean quantizer function calls) - Update xfail reasons to consistent 'Vela compilation fails with Invalid arguments' pattern Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463) cc digantdesai freddan80 per zingo oscarandersson8218 [ghstack-poisoned]

Pull Request resolved: #13789 Add 16A8W quantization support and comprehensive tests for the add operation in ExecutorTorch ARM backend targeting Ethos U55 and U85 NPUs. This follows the pattern established for linear operations, extending int16 support to add operations with hardware-specific testing. Changes: - Add INT16 dtype validation support in op_add.py - Add test_add_tensor_16a8w_tosa_INT test function with U55/U85 pipeline support - Add U55 and U85 specific 16A8W tests with proper xfail decorators - Fix U55/U85 test parameter usage (remove unsupported tosa_extensions, clean quantizer function calls) - Update xfail reasons to consistent 'Vela compilation fails with Invalid arguments' pattern ghstack-source-id: 308053642 ghstack-source-id: 308053642 @exported-using-ghexport @bypass-github-pytorch-ci-checks @bypass-github-pytorch-ci-checks @bypass-github-executorch-ci-checks Differential Revision: [D80510463](https://our.internmc.facebook.com/intern/diff/D80510463/)

facebook-github-bot · 2025-09-07T03:57:48Z

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

@Ninja91

This PR was created by the merge bot to help merge the original PR into the main branch. ghstack PR number: #13789 by @Ninja91 ^ Please use this as the source of truth for the PR details, comments, and reviews ghstack PR base: https://github.com/pytorch/executorch/tree/gh/Ninja91/5/base ghstack PR head: https://github.com/pytorch/executorch/tree/gh/Ninja91/5/head Merge bot PR base: https://github.com/pytorch/executorch/tree/main Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/Ninja91/5/orig @diff-train-skip-merge Co-authored-by: Nitin Jain <[email protected]>

Ninja91 requested a review from digantdesai as a code owner August 29, 2025 04:20

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 29, 2025

facebook-github-bot added the fb-exported label Aug 29, 2025

Ninja91 mentioned this pull request Aug 29, 2025

Add 16A8W support and test for add operation #13653

Closed

zingo added ciflow/trunk partner: arm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Arm module: arm Issues related to arm backend labels Aug 29, 2025

zingo changed the title ~~Add 16A8W support and test for add operation~~ Arm backend: Add 16A8W support and test for add operation Aug 29, 2025

Ninja91 mentioned this pull request Sep 4, 2025

Add 16A8W quantization configuration utility for ARM backend #13898

Open

Ninja91 added the release notes: arm Changes to the ARM backend delegate label Sep 5, 2025

facebook-github-bot merged commit 66e38a9 into gh/Ninja91/5/base Sep 7, 2025
290 of 294 checks passed

facebook-github-bot deleted the gh/Ninja91/5/head branch September 7, 2025 06:41

facebook-github-bot temporarily deployed to cherry-pick-bot September 7, 2025 06:41 — with GitHub Actions Inactive

pytorchbot mentioned this pull request Sep 7, 2025

Arm backend: Add 16A8W support and test for add operation #14039

Merged

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

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

Uh oh!

Conversation

Ninja91 commented Aug 29, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

pytorch-bot bot commented Aug 29, 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/13789

❌ 3 New Failures, 1 Cancelled Job

Uh oh!

facebook-github-bot commented Aug 29, 2025

Uh oh!

facebook-github-bot commented Aug 29, 2025

Uh oh!

facebook-github-bot commented Aug 29, 2025

Uh oh!

facebook-github-bot commented Aug 29, 2025

Uh oh!

Ninja91 commented Aug 29, 2025

Uh oh!

facebook-github-bot commented Sep 4, 2025

Uh oh!

facebook-github-bot commented Sep 4, 2025

Uh oh!

facebook-github-bot commented Sep 4, 2025

Uh oh!

facebook-github-bot commented Sep 4, 2025

Uh oh!

facebook-github-bot commented Sep 5, 2025

Uh oh!

facebook-github-bot commented Sep 6, 2025

Uh oh!

facebook-github-bot commented Sep 7, 2025

Uh oh!

facebook-github-bot commented Sep 7, 2025

Uh oh!

facebook-github-bot commented Sep 7, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

Ninja91 commented Aug 29, 2025 •

edited

Loading

pytorch-bot bot commented Aug 29, 2025 •

edited

Loading