tmoreau89 commented on pull request #7326: URL: https://github.com/apache/tvm/pull/7326#issuecomment-766495174
@merrymercy Verified autotuning vs. autoscheduling on mobilenet model from gluon model zoo: AutoTVM performance (1500 trials per task) is 78ms. Autoscheduler performance (20000 trials total) is 42.52ms. ---------------------------------------------------------------- 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]
