Arm backend: Add 16A8W support for view and transpose operations #14216
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
Pull Request resolved: #13796 Add 16A8W quantization support and test for the sigmoid operation in ExecutorTorch ARM backend. This follows the pattern established for linear and mul operations, extending int16 support to sigmoid operations. Changes: - Add INT16 dtype validation support in op_sigmoid.py - Add test_sigmoid_tensor_16a8w_tosa_INT test function - Enable test_sigmoid.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: 308986667 @exported-using-ghexport Differential Revision: [D80510729](https://our.internmc.facebook.com/intern/diff/D80510729/)
Pull Request resolved: #13797 Add 16A8W quantization support and test for the tanh operation in ExecutorTorch ARM backend. This follows the pattern established for linear, mul, and sigmoid operations, extending int16 support to tanh operations. Changes: - Add INT16 dtype validation support in op_tanh.py - Add test_tanh_tensor_16a8w_tosa_INT test function - Enable test_tanh.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: 308986671 @exported-using-ghexport Differential Revision: [D80510815](https://our.internmc.facebook.com/intern/diff/D80510815/)
Pull Request resolved: #13798 Add 16A8W quantization support and test for the slice operation in ExecutorTorch ARM backend. This follows the pattern established for linear, mul, sigmoid, and tanh operations, extending int16 support to slice operations. Changes: - Add INT16 dtype validation support in op_slice.py - Add test_slice_tensor_16a8w_tosa_INT test function - Enable test_slice.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: 308986668 @exported-using-ghexport Differential Revision: [D80511095](https://our.internmc.facebook.com/intern/diff/D80511095/)
Pull Request resolved: #13799 Add 16A8W quantization support for view and transpose operations in ExecutorTorch ARM backend. This follows the pattern established for linear, mul, sigmoid, tanh, and slice operations, extending int16 support to view and transpose operations. Changes: - Add INT16 dtype validation support in op_transpose.py - Add test_view_tensor_16a8w_tosa_INT test function - Enable test_view.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: 308986670 @exported-using-ghexport Differential Revision: [D80511313](https://our.internmc.facebook.com/intern/diff/D80511313/)
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14216
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New Failure, 9 Pending, 1 Unrelated FailureAs of commit 8ff1bf1 with merge base 1d37845 ( NEW FAILURE - The following job has failed:
BROKEN TRUNK - The following job 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. |
meta-cla
bot
added
the
CLA Signed
Ninja91
approved these changes
Sep 11, 2025
StrycekSimon
pushed a commit
to nxp-upstream/executorch
that referenced
this pull request
Sep 23, 2025
…orch#14216) This PR was created by the merge bot to help merge the original PR into the main branch. ghstack PR number: pytorch#13799 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/Ninja91/12/base ghstack PR head: https://github.com/pytorch/executorch/tree/gh/Ninja91/12/head Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/Ninja91/11/orig Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/Ninja91/12/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.
This PR was created by the merge bot to help merge the original PR into the main branch.
ghstack PR number: #13799 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/Ninja91/12/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/Ninja91/12/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/Ninja91/11/orig
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/Ninja91/12/orig
@diff-train-skip-merge