fix the llm test failing issue + add back cu126/cu128

[lanluo-nvidia]

Description

AttributeError: module 'torch._inductor.fx_passes' has no attribute 'reinplace'

Fixes # (issue)

Type of change

Please delete options that are not relevant and/or add your own.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

Checklist:

• My code follows the style guidelines of this project (You can use the linters)
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas and hacks
• I have made corresponding changes to the documentation
• I have added tests to verify my fix or my feature
• New and existing unit tests pass locally with my changes
• I have added the relevant labels to my PR in so that relevant reviewers are notified

[github-actions]

There are some changes that do not conform to Python style guidelines:

--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/lowering/passes/_FakeTensorUpdater.py	2026-03-05 18:38:18.298241+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/lowering/passes/_FakeTensorUpdater.py	2026-03-05 18:38:55.444799+00:00
@@ -18,10 +18,11 @@
from torch.utils._ordered_set import OrderedSet

# Try to import reinplace module - may not be available in all PyTorch builds
try:
    import importlib
+
    reinplace_module = importlib.import_module("torch._inductor.fx_passes.reinplace")
    _generalized_scatter = getattr(reinplace_module, "_generalized_scatter", None)
except Exception:
    _generalized_scatter = None

@@ -165,11 +166,14 @@
            # or operator.getitem which is used when returning multiple
            # tensors from an op.
            return node.op == "call_function" and (
                isinstance(node.target, torch._ops.OpOverload)
                or node.target is operator.getitem
-                or (_generalized_scatter is not None and node.target is _generalized_scatter)
+                or (
+                    _generalized_scatter is not None
+                    and node.target is _generalized_scatter
+                )
            )

        to_process = OrderedSet[int]()
        for node in self.graph.nodes:
            # NB: Be very careful about skipping nodes (via continues) here

[github-actions]

There are some changes that do not conform to Python style guidelines:

--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/lowering/passes/_FakeTensorUpdater.py	2026-03-05 20:28:58.533773+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/lowering/passes/_FakeTensorUpdater.py	2026-03-05 20:29:32.293886+00:00
@@ -18,10 +18,11 @@
from torch.utils._ordered_set import OrderedSet

# Try to import reinplace module - may not be available in all PyTorch builds
try:
    import importlib
+
    reinplace_module = importlib.import_module("torch._inductor.fx_passes.reinplace")
    _generalized_scatter = getattr(reinplace_module, "_generalized_scatter", None)
except Exception:
    _generalized_scatter = None

@@ -165,11 +166,14 @@
            # or operator.getitem which is used when returning multiple
            # tensors from an op.
            return node.op == "call_function" and (
                isinstance(node.target, torch._ops.OpOverload)
                or node.target is operator.getitem
-                or (_generalized_scatter is not None and node.target is _generalized_scatter)
+                or (
+                    _generalized_scatter is not None
+                    and node.target is _generalized_scatter
+                )
            )

        to_process = OrderedSet[int]()
        for node in self.graph.nodes:
            # NB: Be very careful about skipping nodes (via continues) here