--------- Co-authored-by: Nikhil Mehta <nikmehta@tesla.com>
* Added groups to 2-D convolutions. Only implemented for **some** specializations. Also fixed 1D grouped convs with different kernel strides and added more tests. * fix channels condition
* Init steel conv and update Conv primitive * Update slow CPU implementation to support flipping and input dilation winograd conv routing Co-authored-by: Awni Hannun <awni@apple.com>