Hello, I just saw the overall diagram of Matmul Layer in your github website(https://github.com/microsoft/microxcaling/blob/main/images/rounding_and_quantizing_optns_matmul.png)
But after I checked the matmul.py,
I saw some inconsistencies between the diagram and the code.
In line number 33 of 'matmul.py'(https://github.com/microsoft/microxcaling/blob/main/mx/matmul.py#L33),
I saw that
'assert mode_config in ["aa", "aw", "wa"]'
but the diagram shows mode_config of "aa", "ww", "wa".
I want to make sure which one is right.
Thank you in advance.