-
Notifications
You must be signed in to change notification settings - Fork 536
Fix coreml rank0 #10534
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 coreml rank0 #10534
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/10534
Note: Links to docs will display an error until the docs builds have been completed. ⏳ No Failures, 6 PendingAs of commit b10783e with merge base c5dd476 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
051daa0
to
65171cc
Compare
10e7aa5
to
b10783e
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.
Thanks for the neat fix! Yes wrapping also in coreml delegate runtime is a neat solution
coremltools wraps rank 0 tensors as rank1 tensors in the AOT flow when producing a PTE file. This PR:
Fixes #10451