-
Notifications
You must be signed in to change notification settings - Fork 91
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
#15863: Implementing the view operation #15865
Conversation
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.
Clang-Tidy
found issue(s) with the introduced code (1/1)
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.
Clang-Tidy
found issue(s) with the introduced code (1/1)
…/tt-metal into jvega/view_op_implementation
…/tt-metal into jvega/view_op_implementation
@pytest.mark.parametrize( | ||
"input_shape, output_shape, layout", | ||
[ | ||
((1, 15), (15,), ttnn.ROW_MAJOR_LAYOUT), # RM_last dimension matches, 1D output |
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.
could add test which demonstrates that it will throw if I pass wrong dimensions?
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.
That is done in test_invalid_cases
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.
I just saw it! thanks.
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, but added 1 comment
I am waiting for post commit to run again before merging, I'm a little paranoid with the simple shape change |
Ticket
#15863
Problem description
Models team has asked for a 0-cost view op which asserts out if a 0 cost view is not possible for that request
What's changed
Implemented 0-cost view that provides the proper input validation and then calls the perform_view function in reshape
Checklist