Add 16A8W support and test for sigmoid operation

Summary:
Add 16A8W quantization support and test for the sigmoid operation in ExecutorTorch ARM backend.

This follows the pattern established for linear and mul operations, extending int16 support to sigmoid operations.

Changes:
- Add INT16 dtype validation support in op_sigmoid.py
- Add test_sigmoid_tensor_16a8w_tosa_INT test function
- Enable test_sigmoid.py in test targets configuration

The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency.

Differential Revision: D80510729

Author: Ninja91

backends/arm/test/ops/test_sigmoid.py

@@ -9,14 +9,20 @@
 from typing import Tuple
 
 import torch
-from executorch.backends.arm.test import common
+from executorch.backends.arm.quantizer.arm_quantizer import (
+    get_symmetric_a16w8_quantization_config,
+    TOSAQuantizer,
+)
+from executorch.backends.arm.test import common, conftest
 from executorch.backends.arm.test.tester.test_pipeline import (
     EthosU55PipelineINT,
     EthosU85PipelineINT,
     TosaPipelineFP,
     TosaPipelineINT,
     VgfPipeline,
 )
+from executorch.backends.arm.tosa_specification import TosaSpecification
+from executorch.backends.xnnpack.test.tester import Quantize
 
 aten_op = "torch.ops.aten.sigmoid.default"  # Used for checking that we do not have softmax in the graph after decompose
 exir_op = "executorch_exir_dialects_edge__ops_aten_sigmoid_default"
@@ -253,3 +259,48 @@ def test_sigmoid_vgf_INT_add_3():
         tosa_version="TOSA-1.0+INT",
     )
     pipeline.run()
+
+
+def get_symmetric_a16w8_sigmoid_quantizer(
+    u55_config=False, per_channel_quantization=False
+):
+    tosa_version = conftest.get_option("tosa_version")
+    tosa_profiles = {
+        "1.0": TosaSpecification.create_from_string("TOSA-1.0+INT+int16"),
+    }
+
+    quantizer = TOSAQuantizer(tosa_profiles[tosa_version])
+    quantizer.set_global(
+        get_symmetric_a16w8_quantization_config(is_per_channel=per_channel_quantization)
+    )
+
+    return Quantize(
+        quantizer,
+        get_symmetric_a16w8_quantization_config(
+            is_per_channel=per_channel_quantization
+        ),
+    )
+
+
+@common.parametrize("test_data", test_data_suite)
+def test_sigmoid_16a8w_tosa_INT(test_data: torch.Tensor):
+    """Test sigmoid operation with 16A8W quantization (16-bit activations, 8-bit weights)"""
+    per_channel_quantization = False
+
+    pipeline = TosaPipelineINT[input_t1](
+        Sigmoid(),
+        (test_data(),),
+        aten_op,
+        exir_op=[],
+        per_channel_quantization=per_channel_quantization,
+        use_to_edge_transform_and_lower=True,
+        tosa_extensions=["int16"],
+    )
+
+    pipeline.change_args(
+        "quantize",
+        get_symmetric_a16w8_sigmoid_quantizer(
+            per_channel_quantization=per_channel_quantization
+        ),
+    )
+    pipeline.run()