sunggg commented on PR #15462:
URL: https://github.com/apache/tvm/pull/15462#issuecomment-1663368369

   > Thanks, I understand that there are existing APIs for finding the best 
algorithm, but my confusion lies in determining when to incorporate the 
find_best_algo function. In certain inference frameworks, they utilize a static 
flag to enable algorithm discovery during the warmup phase. but I don't no if 
tvm can enable this at runtime.
   
   Ah, I see. Ideally, it would be good to hide warm-up overhead in the compile 
time if possible. I haven't tried but would it be possible if we run 
`find_best_algo` function in `cuDNNJSONSerializer` at compile-time and then 
pass the best one to the runtime as a JSON node attribute? 


-- 
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]

Reply via email to