Lunderberg commented on issue #17248: URL: https://github.com/apache/tvm/issues/17248#issuecomment-2272112945
This doesn't seem unreasonable, given that the test arrays are very small, and the cuda inference function has data transfer overhead that isn't present on CPU. (One moment as I test and confirm that.) -- 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]
