torch.nn.ReplicationPad3d fails at runtime when there is padding

## 🐞Describing the bug
torch.nn.ReplicationPad3d fails at runtime when there is padding, but ideally it would fail ahead of time.

## To Reproduce
```

import torch

class Model(torch.nn.Module):
def __init__(self):
super().__init__()
self.pad = torch.nn.ReplicationPad3d(padding=2)

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

model = Model()
inputs = (
torch.randn(1, 6, 6, 6, 6),
)

eager_outputs = model(*inputs)
#print(f"Eager: {eager_outputs.shape} {eager_outputs}")

ep = torch.export.export(model.eval(), inputs)
print(ep)

import coremltools as ct
import numpy as np
ep = ep.run_decompositions({})

mlmodel = ct.convert(ep)

coreml_inputs = mlmodel.get_spec().description.input
coreml_outputs = mlmodel.get_spec().description.output
predict_inputs = {str(ct_in.name): pt_in.detach().cpu().numpy().astype(np.int32) for ct_in, pt_in in zip(coreml_inputs, inputs)}
out = mlmodel.predict(predict_inputs)

print("CoremL", out)
```

This fails at runtime with the following error, but ideally it would fail ahead of time during mlmodel creation:

```
/opt/miniconda3/envs/op-et/lib/python3.10/site-packages/coremltools/models/model.py:560: RuntimeWarning: You will not be able to run predict() on this Core ML model. Underlying exception message was: Error compiling model: "Failed to parse the model specification. Error: Unable to parse ML Program: in operation pad_cast_fp16: Padding for more than two dimensions only supports `constant` mode".
_warnings.warn(
Traceback (most recent call last):
File "/Users/scroy/Desktop/executorch/test.py", line 158, in
out = mlmodel.predict(predict_inputs)
File "/opt/miniconda3/envs/op-et/lib/python3.10/site-packages/coremltools/models/model.py", line 804, in predict
raise self._framework_error
File "/opt/miniconda3/envs/op-et/lib/python3.10/site-packages/coremltools/models/model.py", line 549, in _get_proxy_and_spec
_MLModelProxy(
RuntimeError: Error compiling model: "Failed to parse the model specification. Error: Unable to parse ML Program: in operation pad_cast_fp16: Padding for more than two dimensions only supports `constant` mode".
```

## System environment (please complete the following information):
- coremltools version: 8.3
- OS (e.g. MacOS version or Linux type): macOS15

Start with the provided torch.nn.ReplicationPad3d reproduction and follow the ep.run_decompositions({}) to ct.convert(ep) path. Inspect how this padding operation is validated during conversion; done means unsupported non-constant padding for more than two dimensions is rejected during model creation rather than only when predict() runs.

Written by the indexing model from the issue text.