Adding Test for CadenceWithLayerNormQuantizer

Summary:
Adding test for CadenceWithLayerNormQuantizer. 

https://www.internalfb.com/code/fbsource/[72237310dfd9016b5f54a44d994c8a7065eda5d1]/fbcode/executorch/backends/cadence/aot/quantizer/quantizer.py?lines=296-306

Differential Revision: D88898823

Author: RahulC7

backends/cadence/aot/tests/test_quantizer_ops.py

@@ -56,7 +56,6 @@
     CadenceW8A32MixedQuantizer,  # TODO: T247438158 Add test coverage
     CadenceRmsNormNopQuantizer,  # No-op quantizer, doesn't annotate anything, preserves rms_norm from decomposition
     CadenceWakeWordQuantizer,  # TODO: T247438162 Add test coverage
-    CadenceWithLayerNormQuantizer,  # TODO: T247438410 Add test coverage
 }
 
 
@@ -118,6 +117,15 @@
         # For softmax: only input_activation
         [qconfig_A16.input_activation],
     ),
+    (
+        "layer_norm_A8W8",
+        lambda self: self._build_layer_norm_graph(),
+        CadenceWithLayerNormQuantizer(),
+        torch.ops.aten.layer_norm.default,
+        qconfig_A8W8.output_activation,
+        # For layer_norm: only input_activation (weights/bias are passed as others)
+        [qconfig_A8W8.input_activation],
+    ),
 ]
 
 # Derive the set of tested quantizer classes from the test cases.
@@ -243,6 +251,32 @@ def _build_softmax_graph(self) -> tuple[torch.fx.GraphModule, torch.fx.Node]:
         self.assertEqual(len(softmax_nodes), 1, "Should find exactly one softmax node")
         return gm, softmax_nodes[0]
 
+    def _build_layer_norm_graph(self) -> tuple[torch.fx.GraphModule, torch.fx.Node]:
+        """Build a simple graph with a layer_norm operation."""
+        builder = GraphBuilder()
+        # Input shape: (batch, features)
+        x = builder.placeholder("x", torch.randn(1, 10))
+        # normalized_shape must match the last dimension(s) of input
+        normalized_shape = [10]
+        layer_norm = builder.call_operator(
+            op=torch.ops.aten.layer_norm.default,
+            args=(x, normalized_shape),
+            meta=NodeMetadata(
+                {"source_fn_stack": [("layer_norm", torch.ops.aten.layer_norm.default)]}
+            ),
+        )
+        builder.output([layer_norm])
+        gm = builder.get_graph_module()
+
+        layer_norm_nodes = gm.graph.find_nodes(
+            op="call_function",
+            target=torch.ops.aten.layer_norm.default,
+        )
+        self.assertEqual(
+            len(layer_norm_nodes), 1, "Should find exactly one layer_norm node"
+        )
+        return gm, layer_norm_nodes[0]
+
     @parameterized.expand(QUANTIZER_ANNOTATION_TEST_CASES)
     def test_quantizer_annotation(
         self,