After reading the nimble paper, I would like to ask about 3.5 Symbolic Codegen: 1. How to combine autotvm and nimble? Does the model template and search space need to be reduced by human control? How to find the top 100 schedulers? 2. Can ansor and nimble be combined? If so, how can it be realized? Looking forward for your response, thank you!
--- [Visit Topic](https://discuss.tvm.apache.org/t/codegen-of-nimble/9489/7) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.apache.org/email/unsubscribe/d9fefec4ff16c348414468db7ac2eb83a4f9d08bef84f4f3b76c5e7b694af5a5).
