comaniac commented on a change in pull request #9954:
URL: https://github.com/apache/tvm/pull/9954#discussion_r787010392
##########
File path: python/tvm/relay/op/nn/_nn.py
##########
@@ -1061,6 +1062,83 @@ def compute_space_to_depth(attrs, inputs, out_dtype):
reg.register_injective_schedule("nn.batch_to_space_nd")
[email protected]_legalize("nn.conv2d_backward_weight")
+def legalize_conv2d_backward_weight(attrs, inputs, types):
Review comment:
IIUC, this legalization will replace `conv2d_backward_weight` with a
series of ops (the conv2d backward weight before this PR)? Just for my
education, in this case, if we want to offload this op to CuDNN/CUTLASS (in the
future), we should not run Legalize pass, right?
--
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]
