masahi commented on code in PR #11341:
URL: https://github.com/apache/tvm/pull/11341#discussion_r884482157
##########
python/tvm/relay/op/strategy/generic.py:
##########
@@ -1793,6 +1802,18 @@ def cumsum_strategy(attrs, inputs, out_type, target):
return strategy
+@override_native_generic_func("concat_strategy")
+def concatenate_strategy(attrs, inputs, out_type, target):
+ """concatenate generic strategy"""
+ strategy = _op.OpStrategy()
+ strategy.add_implementation(
+ wrap_compute_concat(topi.concatenate),
+ wrap_topi_schedule(topi.generic.schedule_extern),
Review Comment:
yeah, I think you also need to define `concatenate_strategy` in
`strategy/cuda.py`, and use `topi.cuda.schedule_injective` there. That should
allow using `schedule_injective` here.
In general, if you add a new strategy in `generic.py`, you should also
update gpu strategy in `strategy/cuda.py` as well.
--
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]
