Thanks for the proposal. I think we can use more discussion here. To make progress, it is good trying to divide the argument by points, so we can agree on that.
For example, so instead of saying: register vm allows data flow discovery, but dataflow discovery don't have to be done at the VM level. We break it into two points: - 1) Register vm allows easier dataflow discovery - 2) Dataflow parallel discovery can be done at a higher or lower level and do not have things to do with VM In our case, most people can agree on (1) but not necessarily (2). This way, we can find what we actually agree on more and move on from that point. I do think we should aim to have only one version of VM after we agree on things. Mainly because it is a better way to have the community pushing for a consistent technical direction. -- You are receiving this because you are subscribed to this thread. Reply to this email directly or view it on GitHub: https://github.com/dmlc/tvm/issues/2915#issuecomment-477346122
