AOT plugin: examples with RMSNORM

[bowang007]

Description

This PR includes the AOT Plugin demo for RMSNorm Triton kernel.

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/constant_folding.py	2025-06-12 23:42:18.553208+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/lowering/passes/constant_folding.py	2025-06-12 23:42:47.520072+00:00
@@ -98,16 +98,17 @@
class _TorchTensorRTConstantFolder(ConstantFolder):  # type: ignore[misc]
    def __init__(self, *args: Any, **kwargs: Any) -> None:
        super().__init__(*args, **kwargs)

    def is_impure(self, node: torch.fx.node.Node) -> bool:
-        # Set of known quantization ops to be excluded from constant folding. 
+        # Set of known quantization ops to be excluded from constant folding.
        # Currently, we exclude all quantization ops coming from modelopt library.
        quantization_ops = {}
        try:
-            # modelopt import ensures torch.ops.tensorrt.quantize_op.default is registered 
+            # modelopt import ensures torch.ops.tensorrt.quantize_op.default is registered
            import modelopt.torch.quantization as mtq
+
            assert torch.ops.tensorrt.quantize_op.default
            quantization_ops.add(torch.ops.tensorrt.quantize_op.default)
        except Exception as e:
            pass
        if quantization_ops and node.target in quantization_ops:

[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/constant_folding.py	2025-06-12 23:43:24.402980+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/lowering/passes/constant_folding.py	2025-06-12 23:43:48.369761+00:00
@@ -98,16 +98,17 @@
class _TorchTensorRTConstantFolder(ConstantFolder):  # type: ignore[misc]
    def __init__(self, *args: Any, **kwargs: Any) -> None:
        super().__init__(*args, **kwargs)

    def is_impure(self, node: torch.fx.node.Node) -> bool:
-        # Set of known quantization ops to be excluded from constant folding. 
+        # Set of known quantization ops to be excluded from constant folding.
        # Currently, we exclude all quantization ops coming from modelopt library.
        quantization_ops = {}
        try:
-            # modelopt import ensures torch.ops.tensorrt.quantize_op.default is registered 
+            # modelopt import ensures torch.ops.tensorrt.quantize_op.default is registered
            import modelopt.torch.quantization as mtq
+
            assert torch.ops.tensorrt.quantize_op.default
            quantization_ops.add(torch.ops.tensorrt.quantize_op.default)
        except Exception as e:
            pass
        if quantization_ops and node.target in quantization_ops:

[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/constant_folding.py	2025-06-12 23:43:28.499249+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/lowering/passes/constant_folding.py	2025-06-12 23:43:53.506624+00:00
@@ -98,16 +98,17 @@
class _TorchTensorRTConstantFolder(ConstantFolder):  # type: ignore[misc]
    def __init__(self, *args: Any, **kwargs: Any) -> None:
        super().__init__(*args, **kwargs)

    def is_impure(self, node: torch.fx.node.Node) -> bool:
-        # Set of known quantization ops to be excluded from constant folding. 
+        # Set of known quantization ops to be excluded from constant folding.
        # Currently, we exclude all quantization ops coming from modelopt library.
        quantization_ops = {}
        try:
-            # modelopt import ensures torch.ops.tensorrt.quantize_op.default is registered 
+            # modelopt import ensures torch.ops.tensorrt.quantize_op.default is registered
            import modelopt.torch.quantization as mtq
+
            assert torch.ops.tensorrt.quantize_op.default
            quantization_ops.add(torch.ops.tensorrt.quantize_op.default)
        except Exception as e:
            pass
        if quantization_ops and node.target in quantization_ops: