refactor(export): replay the captured kwargs as they are, cache included

The probe now runs layer_inputs[0] verbatim instead of substituting a fresh
past_key_values. A cache only reaches here when the calibration forward loop
left caching on, and by then the layer's amax is already wrong -- every replay
attended over the keys its own earlier replay wrote. Papering over that in
export hides it behind a checkpoint that loads and runs.

PR #2248 owns the real fix and warns at the calibration entry point, which is
where a user can act on it. Letting the probe raise is the better failure until
then: loud, and pointing at the run that produced it.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Signed-off-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com>

Author: Fridah-nv

modelopt/torch/export/layerwise_export.py

@@ -290,14 +290,6 @@ def _fuse_shared_input_scales(self, layer_module: nn.Module, layer_inputs: list
             )
 
         args, kwargs = layer_inputs[0]
-        # A throwaway forward has no use for a cache, and the captured one is not empty:
-        # calibration already replayed these tuples through it, so attending over it would
-        # give the probe twice the key length the captured mask was built for. Cache.reset()
-        # is not an option -- it zeroes the tensors but keeps their length.
-        if kwargs.get("past_key_values") is not None:
-            kwargs = dict(kwargs)
-            kwargs["past_key_values"] = None
-
         input_to_linear, _ = collect_shared_input_modules(
             layer_module, lambda: layer_module(*args, **kwargs)
         )