You are viewing a plain text version of this content. The canonical link for it is here.

Posted to commits@tvm.apache.org by GitBox <gi...@apache.org> on 2021/12/16 18:05:58 UTC

[GitHub] [tvm] comaniac commented on issue #9715: [Bug] Te.gradient not work with complex forward workload

comaniac commented on issue #9715:
URL: https://github.com/apache/tvm/issues/9715#issuecomment-996055035


   It looks like auto-scheduler has issues when generating the schedule sketch for this workload. You could first try to build and run this workload on CPU without tuning to see if we could identify the problem. If that doesn't work, then it must be something wrong with the workload or te.gradient. Otherwise, we could investigate the compute DAG to see why auto-scheduler failed to work on this workload generated by te.gradient.


-- 
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: commits-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org