Add 16A8W support and test for add operation#13653
Closed
Ninja91 wants to merge 4 commits intogh/Ninja91/2/basefrom
Closed
Add 16A8W support and test for add operation#13653Ninja91 wants to merge 4 commits intogh/Ninja91/2/basefrom
Ninja91 wants to merge 4 commits intogh/Ninja91/2/basefrom
Conversation
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]
Ninja91
added a commit
that referenced
this pull request
Aug 25, 2025
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/13653
Note: Links to docs will display an error until the docs builds have been completed. ❌ 4 New FailuresAs of commit 2e94ad7 with merge base 9053089 ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D80510463 |
This PR needs a
|
This was referenced Aug 26, 2025
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]
Ninja91
added a commit
that referenced
this pull request
Aug 26, 2025
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/)
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D80510463 |
digantdesai
reviewed
Aug 26, 2025
digantdesai
requested changes
Aug 26, 2025
Contributor
digantdesai
left a comment
digantdesai
left a comment
There was a problem hiding this comment.
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]
Contributor
|
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]
Ninja91
added a commit
that referenced
this pull request
Aug 27, 2025
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/)
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D80510463 |
Contributor
Author
|
CLosing this as I have updated PR here: #13789 |
Ninja91
had a problem deploying
to
cherry-pick-bot
GitHub Actions
Failure
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Stack from ghstack (oldest at bottom):
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:
The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency.
Differential Revision: D80510463