Thanks a lot for working on this, this is going to be really impactful, especially toward supporting NLP models. I have a couple of questions:
1. Can you please explain the shape function in a little more detail? What exactly is its purpose? Will it have to be registered for every op? 2. Some ops, like `full` take their shape argument as a constant list. With this change, we could potentially support either a constant list or a relay expression that is unknown at compile time. How would that work? Would the operator definition have to change? -- 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/4118#issuecomment-545681963
