-
Notifications
You must be signed in to change notification settings - Fork 537
[ExecuTorch][XNNPACK] Don't partition per_tensor weights with qd8 #8787
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
Conversation
This is not supported, so we shouldn't partition it. Add an expectedFailure test to indicate that this is not supported. Differential Revision: [D70343584](https://our.internmc.facebook.com/intern/diff/D70343584/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/8787
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 1b91adb with merge base 542480c ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This is not supported, so we shouldn't partition it. Add an expectedFailure test to indicate that this is not supported. Differential Revision: [D70343584](https://our.internmc.facebook.com/intern/diff/D70343584/) ghstack-source-id: 268822901 Pull Request resolved: #8787
This pull request was exported from Phabricator. Differential Revision: D70343584 |
…ith qd8" This is not supported, so we shouldn't partition it. Add an expectedFailure test to indicate that this is not supported. Differential Revision: [D70343584](https://our.internmc.facebook.com/intern/diff/D70343584/) [ghstack-poisoned]
Pull Request resolved: #8787 This is not supported, so we shouldn't partition it. Add an expectedFailure test to indicate that this is not supported. ghstack-source-id: 268894461 @exported-using-ghexport Differential Revision: [D70343584](https://our.internmc.facebook.com/intern/diff/D70343584/)
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.
nice change, i didn't add these types of checks when i first added this because it was going to be too tedious along with all the other refactoring i had to do, so I kind of left this as a todo, when users encounter it.
No worries. I started to feel gemm_config needs a refactor. It is too complex now. 😃 |
…ith qd8" This is not supported, so we shouldn't partition it. Add an expectedFailure test to indicate that this is not supported. Differential Revision: [D70343584](https://our.internmc.facebook.com/intern/diff/D70343584/) [ghstack-poisoned]
…ith qd8" This is not supported, so we shouldn't partition it. Add an expectedFailure test to indicate that this is not supported. Differential Revision: [D70343584](https://our.internmc.facebook.com/intern/diff/D70343584/) [ghstack-poisoned]
@digantdesai perhaps we can add a util function that goes through all the quant/dequant nodes in the partition, and validates those. And we can call that for every quantized op |
Summary: This is not supported, so we shouldn't partition it. Add an expectedFailure test to indicate that this is not supported. ghstack-source-id: 269356867 exported-using-ghexport Reviewed By: mcr229 Differential Revision: D70343584
Summary: Pull Request resolved: pytorch#8787 This is not supported, so we shouldn't partition it. Add an expectedFailure test to indicate that this is not supported. ghstack-source-id: 269356867 exported-using-ghexport Reviewed By: mcr229 Differential Revision: D70343584
Stack from ghstack (oldest at bottom):
This is not supported, so we shouldn't partition it.
Add an expectedFailure test to indicate that this is not supported.
Differential Revision: D70343584