support 1D tensors in ttnn

[davorchap]

User should be able to specify a 1D tensor shape , such as (10) , today it has to be specified as 2D (1,10)

[arakhmati]

We support 1D row-major tensors. Tilized tensors have to be 2D

[davorchap]

We support 1D row-major tensors. Tilized tensors have to be 2D

Thanks @arakhmati

Perhaps the original shape after tilizing+padding would still be 1D? We change the layout but the original would still be 1D

@razorback3 fyi

[razorback3]

What our suggestion is: 1D row-major tensor after padding and tilizing -> 2D tensor But, if we call _shape_withoutpadding() it returns 1D tensor

[blueblud7]

@davorchap Would you please share any update regarding @razorback3's comment?

[davorchap]

@davorchap Would you please share any update regarding @razorback3's comment?

Yes, 1D original tensor shape will be preserved.

@nsmithtt , @arakhmati and team are working through a proposal to uplift the Tensor class to support this cleanly

[ayerofieiev-tt]

@arakhmati @eyonland @yan-zaretskiy for vis for Tensor layout conversation

[arakhmati]

We can't change the dimensionality of the shape when calling shape_without_padding because it will be misleading in many other cases. And it really doesn't make sense to get tilized tensor's shape as 1D. I think Moreh should add a free function that does what's required and use it in appropriate places. This can't be a part of our infra as of right now