echuraev commented on pull request #8313: URL: https://github.com/apache/tvm/pull/8313#issuecomment-870458257
> Minor nit. > > In general, I see the utility for single Relay kernels that have too many inputs, but I wonder if you'll hit this more for kernels post-fusion. This doesn't seem to tackle that for anything other than giant concatenation? Yes, now it is solving only problem with concat layer. I thought that maybe this pass can be useful in case of split layer for example. But I wasn't able to reproduce the same problem for a split layer on several simple tests. -- 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]
