-
Notifications
You must be signed in to change notification settings - Fork 537
[TOSA] Replace Linear lowering of using Matmul with FullyConnected #616
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
✅ Deploy Preview for resplendent-gnome-14e531 ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
lgtm, let's try to add tests in case there are breakages. Looks like there are many if else |
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. Left some comments, OK for now. Add TODOs as required.
But please add torch.nn.Linear
tests with >2 rank.
i.e. copy simple_linear
test into not_so_simple_linear
with
(torch.ones(100, 20),), -> (torch.ones(5, 10, 100, 20),),
there're some large number of test model failures. Don't seem related? (I can't see the errors inside) |
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.
Looks good. Let's restructure and add more tests after MVP. I'm getting lost in the if-else....
I agree. It's a pain 😓 |
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, let mw know when you are ready
@digantdesai has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
@digantdesai has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
No description provided.