-
Notifications
You must be signed in to change notification settings - Fork 458
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
Fix xnnpack pybind #2802
Fix xnnpack pybind #2802
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/2802
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 25e55f2 with merge base 15d9ddd ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
83e5e23
to
bd4e4ef
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM...you tested this fixes the pybind xnnpack issue?
@mcr229 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Summary: As titled. Add executorch/backends/xnnpack/test/models directory into pytest.ini Test Plan: Reviewers: Subscribers: Tasks: Tags:
@mcr229 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Fixing XNNPACK Pybind.
Currently pybindings for xnnpack fail due to uninitialized error. We notice the following:
That is xnn_initialize symbole comes from libtorch_cpu, but when we call xnn_create_subgraph we call it from another library. It seems like explicitly adding XNNPACK to the portable_libs pybind fixes this problem.
Additionaly, we fix some fPIC issues when building XNNPACK.