Fix device handling in `nn.utils.rnn.unpad_sequence` (#98042)
Without this change I get the following error.
```
line 444, in unpad_sequence
mask = idx < length
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!
```
Pull Request resolved: https://github.com/pytorch/pytorch/pull/98042
Approved by: https://github.com/mikaylagawarecki
