feat: support in-place plugins

[bowang007]

Description

End-to-end support for in-place QDP plugins in torch-tensorrt

Fixes #4240

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)
• 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/unfunctionalize_qdp_inplace.py	2026-05-20 14:19:18.477550+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/lowering/passes/unfunctionalize_qdp_inplace.py	2026-05-20 14:19:37.985186+00:00
@@ -131,13 +131,11 @@
                gm.graph.erase_node(user)
        else:
            return_getitems: List[Any] = []
            with gm.graph.inserting_after(new_call):
                for i in range(n_outputs):
-                    g = gm.graph.call_function(
-                        operator.getitem, args=(new_call, i)
-                    )
+                    g = gm.graph.call_function(operator.getitem, args=(new_call, i))
                    if isinstance(hop_val, tuple) and i < len(hop_val):
                        g.meta["val"] = hop_val[i]
                    return_getitems.append(g)
            for user in getitem_users:
                idx = user.args[1]

[narendasan]

Can you explain this lowering pass? Auto functionalization is a bit more broader reaching that just for QDP nodes. Maybe it might be useful elsewhere?

[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/unfunctionalize_qdp_inplace.py	2026-07-14 09:13:16.073785+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/lowering/passes/unfunctionalize_qdp_inplace.py	2026-07-14 09:13:43.216625+00:00
@@ -131,13 +131,11 @@
                gm.graph.erase_node(user)
        else:
            return_getitems: List[Any] = []
            with gm.graph.inserting_after(new_call):
                for i in range(n_outputs):
-                    g = gm.graph.call_function(
-                        operator.getitem, args=(new_call, i)
-                    )
+                    g = gm.graph.call_function(operator.getitem, args=(new_call, i))
                    if isinstance(hop_val, tuple) and i < len(hop_val):
                        g.meta["val"] = hop_val[i]
                    return_getitems.append(g)
            for user in getitem_users:
                idx = user.args[1]