Ops with included input dim order conversion fail at runtime

🐛 Describe the bug

Certain ops in pytorch can internally convert their inputs to contiguous format. Linear, for example, seems to do this. These dim order conversions are reflected in the node metadata (and thus ET dim order), but not in the graph. Our kernels don't include the input dim order conversion and thus fail at runtime.

A slightly contrived example is as follows, though I expect that this is reproable with any op with an ATen kernel that includes an implicit conversion to contiguous, of which there are quite a few.

import torch

class Module(torch.nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = torch.nn.Linear(10, 10)

    def forward(self, x):
        return self.linear(x)

inputs = (torch.randn(1,2,3,10).to(memory_format=torch.channels_last),)
module = Module()

ep = torch.export.export(module, inputs)
from executorch.exir import to_edge_transform_and_lower

et_program = to_edge_transform_and_lower(ep).to_executorch()
from executorch.extension.pybindings.portable_lib import _load_for_executorch_from_buffer

et_model = _load_for_executorch_from_buffer(et_program.buffer)

Output:

[tensor_util_portable.cpp:132] Check failed (all_contiguous || all_channels_last): 2 input tensors have different dim orders
[op_expand_copy.cpp:89] Check failed (tensors_have_same_dim_order(self, out)): 
[method.cpp:1322] KernelCall failed at instruction 0:1 in operator aten::expand_copy.out: 0x12
[method.cpp:1328] arg 0 with type id 1
[method.cpp:1328] arg 1 with type id 8
[method.cpp:1328] arg 2 with type id 5
[method.cpp:1328] arg 3 with type id 1
[method.cpp:1328] arg 4 with type id 1

Note that the failure actually occurs in expand_copy due to the weird decomp in this case.

Versions

N/A

cc @JacobSzwejbka @angelayi

Start with the provided torch.export.export and to_edge_transform_and_lower reproduction, then inspect tensor_util_portable.cpp and op_expand_copy.cpp around the reported failures. Trace how input dim-order metadata reaches the graph and portable kernels. Done means the channels-last Linear example loads and runs without dim-order mismatch errors.