ganler commented on issue #11794: URL: https://github.com/apache/tvm/issues/11794#issuecomment-1180713035
> @ganler Sorry if I understood improperly but the situation here seems to be that the broadcast operation is mismatching, if you want it to output a `int64` tensor shouldn't you use something more like `broadcast_to = relay.broadcast_to(relay.cast(x, dtype="int64"), relay.const(broadcast_shape))`? The example here is not doing integer casting. If we directly use relay, we can of course mark the broadcasting shape as 'int32'. However, external model formats like onnx often bring such 'int64' things (it is not strongly supported but still valid in the relay language) into the relay frontend which fails compilation. -- 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]
