Lunderberg commented on issue #14100: URL: https://github.com/apache/tvm/issues/14100#issuecomment-1454221105
@LeiWang1999 I've only been able to take a quick look so far, but I was able to run the example, and get an error raised from BlockizeTensorize. It looks like the original error may be much earlier, during the call to `sch.compute_at(block_conv_input_frag, kw)`. Prior to this, the `"Apad_shared_wmma.matrix_a"` block has more normal bindings, but this scheduling step introduces the `v1 = T.axis.spatial(16, h + kh)` iterator. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
