tvm
tvm copied to clipboard
[fix] MXNet dot for all tensor dimensions
In this PR problem of MXNet dot for all tensor dimensions is fixed. This PR is related to #11691 issue. Previously, it was only provided the case of 2D tensors, but not 1D and non 2D tensors and their combinations. This is provided now.
Any feedback about this PR? I know you have more important work to do and that's why this is waiting.
cc: @masahi @junrushao1994 @kevinthesun
I think this PR is correct now. The problem was trivial about the structure of the code that lint tests suggested. Please, take a look now if you can.
cc: @masahi @kevinthesun @junrushao
I rebased and all checks are good now again.
@areusch @masahi