Has anyone successfully attempted a torch.jit.trace or torch.onnx.export of a UDOP model?

[plamb-viso]

I am currently loading the checkpoint on huggingface udop-unimodel-large-224 and immediately trying to torch.jit.trace or torch.onnx.export it with input data provided for the input_ids, attention_mask, labels, seg_data, visual_seg_data, decoder_attention_mask and image fields (for the forward function -- note these are the same fields used in the rvlcdip example). I'm running into a variety of issues, most commonly:

RuntimeError: 0 INTERNAL ASSERT FAILED at "/Users/runner/work/pytorch/pytorch/pytorch/torch/csrc/jit/ir/alias_analysis.cpp":614, please report a bug to PyTorch. We don't have an op for aten::full_like but it isn't a special case.  Argument types: Tensor, bool, int, int, Device, bool, NoneType,

Curious if anyone has successfully traced the UDOP model and has a code example. I cannot find one in the i-Code repository.