weirdkerneltrick opened a new issue #4556: Tuning group_conv for x86 URL: https://github.com/apache/incubator-tvm/issues/4556 Hello! I've tried to tune VarGFaceNet for fast inference via TVM, but got no speed boost. It seems that tuning group_conv for x86 isn't supported at the moment. Is that so? What can be done to tune VarGFaceNet's group convolutions?
---------------------------------------------------------------- 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] With regards, Apache Git Services
