xutianming commented on issue #6354: URL: https://github.com/apache/incubator-tvm/issues/6354#issuecomment-682582033
I also got similar questions. Same models written in PyTorch (Bert for example) seem to be slower than TensorFlow. As for Relay IR, models from different frontends should be the same. ---------------------------------------------------------------- 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]
