[ET][XNNPACK] Add support for quantized Multiply#104134
[ET][XNNPACK] Add support for quantized Multiply#104134digantdesai wants to merge 1 commit intopytorch:mainfrom
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/104134
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 1bff32e: This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
This pull request was exported from Phabricator. Differential Revision: D46985169 |
e3911db to
917c8db
Compare
|
This pull request was exported from Phabricator. Differential Revision: D46985169 |
917c8db to
bbc6e9f
Compare
|
This pull request was exported from Phabricator. Differential Revision: D46985169 |
bbc6e9f to
523a7b6
Compare
|
This pull request was exported from Phabricator. Differential Revision: D46985169 |
523a7b6 to
b07de1d
Compare
|
This pull request was exported from Phabricator. Differential Revision: D46985169 |
b07de1d to
9a62d94
Compare
|
This pull request was exported from Phabricator. Differential Revision: D46985169 |
9a62d94 to
05d9447
Compare
|
This pull request was exported from Phabricator. Differential Revision: D46985169 |
05d9447 to
5a9a446
Compare
|
This pull request was exported from Phabricator. Differential Revision: D46985169 |
Summary: Pull Request resolved: pytorch#104134 Also adds support for backend_config with relu fusion since XNNPACK allows it. We should revisit the relu fusion once we gain more clarity on quantSrcPartition or some other way to do these fusion and not having to add all combinations. We should really rename the backend config to et_xnnpack.py or something TODO Test Plan: `buck test fbcode//mode/dev-nosan fbcode//executorch/backends/xnnpack/test:` Reviewed By: mcr229 Differential Revision: D46985169 fbshipit-source-id: 74b816e68a412aeccdd5e44450f8ea5aea51e49e
5a9a446 to
1bff32e
Compare
|
This pull request was exported from Phabricator. Differential Revision: D46985169 |
|
@pytorchbot merge (Initiating merge automatically since Phabricator Diff has merged) |
Summary: X-link: pytorch/pytorch#104134 Also adds support for backend_config with relu fusion since XNNPACK allows it. We should revisit the relu fusion once we gain more clarity on quantSrcPartition or some other way to do these fusion and not having to add all combinations. We should really rename the backend config to et_xnnpack.py or something TODO Reviewed By: mcr229 Differential Revision: D46985169 fbshipit-source-id: 30d79d5b5f239545fe5f6619c8047bcb4fc15e5f
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
Summary:
Also adds support for backend_config with relu fusion since XNNPACK allows it.
We should revisit the relu fusion once we gain more clarity on quantSrcPartition or some other way to do these fusion and not having to add all combinations.
We should really rename the backend config to et_xnnpack.py or something TODO
Test Plan:
buck test fbcode//mode/dev-nosan fbcode//executorch/backends/xnnpack/test:Differential Revision: D46985169