Arm backend: Add 16A8W FCNode support with BMM dependency fix #13801
Conversation
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
Add 16A8W quantization support for FCNode operations with BMM dependency fix in ExecutorTorch ARM backend. This follows the pattern established for linear, mul, sigmoid, tanh, slice, view/transpose, and cat operations, extending int16 support to FCNode operations. Changes: - Add INT16 dtype validation support in op_bmm.py - Add test_addmm_tensor_16a8w_tosa_INT test function - Enable test_addmm.py in test targets configuration - Fix BMM dependency for FCNode operations The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency. Differential Revision: [D80512504](https://our.internmc.facebook.com/intern/diff/D80512504/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/13801
Note: Links to docs will display an error until the docs builds have been completed. ❌ 6 New Failures, 1 Cancelled Job, 5 Unrelated FailuresAs of commit 19dd4c6 with merge base 1d37845 ( NEW FAILURES - The following jobs have failed:
CANCELLED JOB - The following job was cancelled. Please retry:
BROKEN TRUNK - The following jobs failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This was referenced Aug 29, 2025
meta-cla
bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D80512504 |
zingo
added
ciflow/trunk
module: arm
zingo
changed the title
digantdesai
reviewed
Aug 29, 2025
digantdesai
reviewed
Aug 29, 2025
digantdesai
approved these changes
Aug 29, 2025
…fix" Add 16A8W quantization support for FCNode operations with BMM dependency fix in ExecutorTorch ARM backend. This follows the pattern established for linear, mul, sigmoid, tanh, slice, view/transpose, and cat operations, extending int16 support to FCNode operations. Changes: - Add INT16 dtype validation support in op_bmm.py - Add test_addmm_tensor_16a8w_tosa_INT test function - Enable test_addmm.py in test targets configuration - Fix BMM dependency for FCNode operations The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency. Differential Revision: [D80512504](https://our.internmc.facebook.com/intern/diff/D80512504/) cc digantdesai freddan80 per zingo oscarandersson8218 [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D80512504 |
…fix" Add 16A8W quantization support for FCNode operations with BMM dependency fix in ExecutorTorch ARM backend. This follows the pattern established for linear, mul, sigmoid, tanh, slice, view/transpose, and cat operations, extending int16 support to FCNode operations. Changes: - Add INT16 dtype validation support in op_bmm.py - Add test_addmm_tensor_16a8w_tosa_INT test function - Enable test_addmm.py in test targets configuration - Fix BMM dependency for FCNode operations The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency. Differential Revision: [D80512504](https://our.internmc.facebook.com/intern/diff/D80512504/) cc digantdesai freddan80 per zingo oscarandersson8218 [ghstack-poisoned]
Ninja91
added a commit
that referenced
this pull request
Sep 5, 2025
Pull Request resolved: #13801 Add 16A8W quantization support for FCNode operations with BMM dependency fix in ExecutorTorch ARM backend. This follows the pattern established for linear, mul, sigmoid, tanh, slice, view/transpose, and cat operations, extending int16 support to FCNode operations. Changes: - Add INT16 dtype validation support in op_bmm.py - Add test_addmm_tensor_16a8w_tosa_INT test function - Enable test_addmm.py in test targets configuration - Fix BMM dependency for FCNode operations The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency. ghstack-source-id: 307685860 @exported-using-ghexport Differential Revision: [D80512504](https://our.internmc.facebook.com/intern/diff/D80512504/)
|
This pull request was exported from Phabricator. Differential Revision: D80512504 |
…fix" Add 16A8W quantization support for FCNode operations with BMM dependency fix in ExecutorTorch ARM backend. This follows the pattern established for linear, mul, sigmoid, tanh, slice, view/transpose, and cat operations, extending int16 support to FCNode operations. Changes: - Add INT16 dtype validation support in op_bmm.py - Add test_addmm_tensor_16a8w_tosa_INT test function - Enable test_addmm.py in test targets configuration - Fix BMM dependency for FCNode operations The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency. Differential Revision: [D80512504](https://our.internmc.facebook.com/intern/diff/D80512504/) cc digantdesai freddan80 per zingo oscarandersson8218 [ghstack-poisoned]
Ninja91
added a commit
that referenced
this pull request
Sep 5, 2025
Pull Request resolved: #13801 Add 16A8W quantization support for FCNode operations with BMM dependency fix in ExecutorTorch ARM backend. This follows the pattern established for linear, mul, sigmoid, tanh, slice, view/transpose, and cat operations, extending int16 support to FCNode operations. Changes: - Add INT16 dtype validation support in op_bmm.py - Add test_addmm_tensor_16a8w_tosa_INT test function - Enable test_addmm.py in test targets configuration - Fix BMM dependency for FCNode operations The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency. ghstack-source-id: 307686817 @exported-using-ghexport Differential Revision: [D80512504](https://our.internmc.facebook.com/intern/diff/D80512504/)
|
This pull request was exported from Phabricator. Differential Revision: D80512504 |
…fix" Add 16A8W quantization support for FCNode operations with BMM dependency fix in ExecutorTorch ARM backend. This follows the pattern established for linear, mul, sigmoid, tanh, slice, view/transpose, and cat operations, extending int16 support to FCNode operations. Changes: - Add INT16 dtype validation support in op_bmm.py - Add test_addmm_tensor_16a8w_tosa_INT test function - Enable test_addmm.py in test targets configuration - Fix BMM dependency for FCNode operations The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency. Differential Revision: [D80512504](https://our.internmc.facebook.com/intern/diff/D80512504/) cc digantdesai freddan80 per zingo oscarandersson8218 [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D80512504 |
…fix" Add 16A8W quantization support for FCNode operations with BMM dependency fix in ExecutorTorch ARM backend. This follows the pattern established for linear, mul, sigmoid, tanh, slice, view/transpose, and cat operations, extending int16 support to FCNode operations. Changes: - Add INT16 dtype validation support in op_bmm.py - Add test_addmm_tensor_16a8w_tosa_INT test function - Enable test_addmm.py in test targets configuration - Fix BMM dependency for FCNode operations The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency. Differential Revision: [D80512504](https://our.internmc.facebook.com/intern/diff/D80512504/) cc digantdesai freddan80 per zingo oscarandersson8218 [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D80512504 |
…fix" Add 16A8W quantization support for FCNode operations with BMM dependency fix in ExecutorTorch ARM backend. This follows the pattern established for linear, mul, sigmoid, tanh, slice, view/transpose, and cat operations, extending int16 support to FCNode operations. Changes: - Add INT16 dtype validation support in op_bmm.py - Add test_addmm_tensor_16a8w_tosa_INT test function - Enable test_addmm.py in test targets configuration - Fix BMM dependency for FCNode operations The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency. Differential Revision: [D80512504](https://our.internmc.facebook.com/intern/diff/D80512504/) cc digantdesai freddan80 per zingo oscarandersson8218 [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D80512504 |
…fix" Add 16A8W quantization support for FCNode operations with BMM dependency fix in ExecutorTorch ARM backend. This follows the pattern established for linear, mul, sigmoid, tanh, slice, view/transpose, and cat operations, extending int16 support to FCNode operations. Changes: - Add INT16 dtype validation support in op_bmm.py - Add test_addmm_tensor_16a8w_tosa_INT test function - Enable test_addmm.py in test targets configuration - Fix BMM dependency for FCNode operations The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency. Differential Revision: [D80512504](https://our.internmc.facebook.com/intern/diff/D80512504/) cc digantdesai freddan80 per zingo oscarandersson8218 [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D80512504 |
…fix" Add 16A8W quantization support for FCNode operations with BMM dependency fix in ExecutorTorch ARM backend. This follows the pattern established for linear, mul, sigmoid, tanh, slice, view/transpose, and cat operations, extending int16 support to FCNode operations. Changes: - Add INT16 dtype validation support in op_bmm.py - Add test_addmm_tensor_16a8w_tosa_INT test function - Enable test_addmm.py in test targets configuration - Fix BMM dependency for FCNode operations The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency. Differential Revision: [D80512504](https://our.internmc.facebook.com/intern/diff/D80512504/) cc digantdesai freddan80 per zingo oscarandersson8218 [ghstack-poisoned]
Ninja91
added a commit
that referenced
this pull request
Sep 10, 2025
Pull Request resolved: #13801 Add 16A8W quantization support for FCNode operations with BMM dependency fix in ExecutorTorch ARM backend. This follows the pattern established for linear, mul, sigmoid, tanh, slice, view/transpose, and cat operations, extending int16 support to FCNode operations. Changes: - Add INT16 dtype validation support in op_bmm.py - Add test_addmm_tensor_16a8w_tosa_INT test function - Enable test_addmm.py in test targets configuration - Fix BMM dependency for FCNode operations The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency. ghstack-source-id: 308935362 @exported-using-ghexport Differential Revision: [D80512504](https://our.internmc.facebook.com/intern/diff/D80512504/)
|
This pull request was exported from Phabricator. Differential Revision: D80512504 |
…fix" Add 16A8W quantization support for FCNode operations with BMM dependency fix in ExecutorTorch ARM backend. This follows the pattern established for linear, mul, sigmoid, tanh, slice, view/transpose, and cat operations, extending int16 support to FCNode operations. Changes: - Add INT16 dtype validation support in op_bmm.py - Add test_addmm_tensor_16a8w_tosa_INT test function - Enable test_addmm.py in test targets configuration - Fix BMM dependency for FCNode operations The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency. Differential Revision: [D80512504](https://our.internmc.facebook.com/intern/diff/D80512504/) cc digantdesai freddan80 per zingo oscarandersson8218 [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D80512504 |
facebook-github-bot
merged commit cc493b5
into
gh/Ninja91/14/base
290 of 303 checks passed
facebook-github-bot
temporarily deployed
to
cherry-pick-bot
GitHub Actions
Inactive
Ninja91
added a commit
that referenced
this pull request
Sep 11, 2025
This PR was created by the merge bot to help merge the original PR into the main branch. ghstack PR number: #13801 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/Ninja91/14/base ghstack PR head: https://github.com/pytorch/executorch/tree/gh/Ninja91/14/head Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/Ninja91/13/orig Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/Ninja91/14/orig @diff-train-skip-merge --------- Co-authored-by: Nitin Jain <jainnitin@meta.com>
StrycekSimon
pushed a commit
to nxp-upstream/executorch
that referenced
this pull request
Sep 23, 2025
…h#14218) This PR was created by the merge bot to help merge the original PR into the main branch. ghstack PR number: pytorch#13801 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/Ninja91/14/base ghstack PR head: https://github.com/pytorch/executorch/tree/gh/Ninja91/14/head Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/Ninja91/13/orig Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/Ninja91/14/orig @diff-train-skip-merge --------- Co-authored-by: Nitin Jain <jainnitin@meta.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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 for FCNode operations with BMM dependency fix in ExecutorTorch ARM backend.
This follows the pattern established for linear, mul, sigmoid, tanh, slice, view/transpose, and cat operations, extending int16 support to FCNode operations.
Changes:
The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency.
Differential Revision: D80512504
cc @digantdesai @freddan80 @per @zingo @oscarandersson8218