RNN contiguous error issue

[jhnwu3]

return forward_call(*args, **kwargs)
       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/johnwu3/projects/PyHealth_Branch_Testing/PyHealth/pyhealth/models/rnn.py", line 117, in forward
outputs, _ = self.rnn(x)
^^^^^^^^^^^
File "/home/johnwu3/.local/share/virtualenvs/PyHealthAgent-61osKUUg/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/johnwu3/.local/share/virtualenvs/PyHealthAgent-61osKUUg/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/johnwu3/.local/share/virtualenvs/PyHealthAgent-61osKUUg/lib/python3.12/site-packages/torch/nn/modules/rnn.py", line 1405, in forward
result = _VF.gru(
^^^^^^^^
RuntimeError: cuDNN error: CUDNN_STATUS_NOT_SUPPORTED. This error may appear if you passed in a non-contiguous input.

Will ediit to add more details later about reproduction.