That sounds reasonable, but it's not working, as the default behavior in AutoTVM for `ref_input is None` is already using `nd.empty`:
```python args = [nd.empty(x[0], dtype=x[1], ctx=ctx) for x in build_result.arg_info] ``` Maybe the `copyfrom` logic should check the `empty` case, but I haven't looked into it yet. Regarding the performance numbers, the cycle count of `copy=True` and `False` didn't show a difference, so I think it's okay for me as for now. Let's discuss this in detail when I get the PR ready. --- [Visit Topic](https://discuss.tvm.ai/t/do-not-write-tensor-data-in-microtvm-with-autotvm/6109/8) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/98037ae63a07303f1a698bd979d2615b3910b5e400e3a7ecc357e8534ceb7e02).
