tqchen commented on PR #18871:
URL: https://github.com/apache/tvm/pull/18871#issuecomment-3999999256
Thanks for the note, seems keeping lazy is something that is helpful here!
In that case i think converting to lazy by default makes sense
Do we know if we only do lazy but not caching would have similar impact?
Also it is interesting to learn about model used, since 142 t/s sounds like a
reasonably small model. just to understand the state
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
