altanh commented on pull request #7500:
URL: https://github.com/apache/tvm/pull/7500#issuecomment-785326896


   > After a first pass, this looks mostly good to me. Any idea how much 
overhead this brings to running the passes?
   
   I did a few compilation runs on a large model that takes ~50 seconds and 
didn't notice any large performance hits, seemed to be mostly hidden by normal 
compilation variance. In any case, I'm disabling the profiling by default and 
added API to enable/disable as needed. I think this should be good to go for 
now.


----------------------------------------------------------------
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.

For queries about this service, please contact Infrastructure at:
[email protected]


Reply via email to