masahi commented on a change in pull request #9207:
URL: https://github.com/apache/tvm/pull/9207#discussion_r723655456
##########
File path: python/tvm/topi/cuda/batch_matmul.py
##########
@@ -93,6 +93,8 @@ def schedule_batch_matmul(cfg, outs):
def _schedule(cfg, op):
C = op.output(0)
A, B = s[C].op.input_tensors
+ if B.op.tag == "tensor_b_copy":
+ s[B].compute_inline()
Review comment:
Thanks, that seems to work. I'll make this change. I also prefer your
approach since relying on implicit agreement on the tag name is opaque and not
robust.
--
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]
