-
Notifications
You must be signed in to change notification settings - Fork 710
Support 5-input concat in XNNPACK delegate #7401
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Support 5-input concat in XNNPACK delegate #7401
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/7401
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 9ecab98 with merge base 82763a9 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
This pull request was exported from Phabricator. Differential Revision: D67439458 |
Summary: I noticed that support for 5-input concatenate ops was added to the XNNPACK library subgraph layer. We can support this in the delegate. Reviewed By: mcr229 Differential Revision: D67439458
713b5e1 to
0f8f7c3
Compare
|
This pull request was exported from Phabricator. Differential Revision: D67439458 |
Summary: I noticed that support for 5-input concatenate ops was added to the XNNPACK library subgraph layer. We can support this in the delegate. Reviewed By: mcr229 Differential Revision: D67439458
0f8f7c3 to
fae9d64
Compare
|
This pull request was exported from Phabricator. Differential Revision: D67439458 |
Summary: Pull Request resolved: pytorch#7401 I noticed that support for 5-input concatenate ops was added to the XNNPACK library subgraph layer. We can support this in the delegate. Reviewed By: mcr229 Differential Revision: D67439458
|
This pull request was exported from Phabricator. Differential Revision: D67439458 |
fae9d64 to
9ecab98
Compare
|
This pull request was exported from Phabricator. Differential Revision: D67439458 |
Summary: I noticed that support for 5-input concatenate ops was added to the XNNPACK library subgraph layer. We can support this in the delegate.
Differential Revision: D67439458