yongwww commented on pull request #6472: URL: https://github.com/apache/incubator-tvm/pull/6472#issuecomment-693771882
> I mean, what kind of real world PyTorch code ends up generating `copy_`? Nobody writes `torch.copy_()` explicitly right? I won't write model using `torch.copy_()`. seems `copy_` happened in the similar cases to that t-vi provided in real world application. Does keeping clamp_ and removing copy_ sound good to you? I am okay to remove any one of them ---------------------------------------------------------------- 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: us...@infra.apache.org