unified partitioner for qs8 mv2 (#306)

Summary:
Pull Request resolved: #306

Using Unified Partitioner for MV2

Reviewed By: digantdesai

Differential Revision: D49116827

fbshipit-source-id: bbad3b941fb94d05031368fa20f81fcf728b84f4

Author: mcr229

backends/xnnpack/test/models/mobilenet_v2.py

@@ -8,11 +8,7 @@
 
 import torch
 import torchvision.models as models
-from executorch.backends.xnnpack.partition.xnnpack_partitioner import (
-    XnnpackQuantizedPartitioner,
-)
-from executorch.backends.xnnpack.test.tester import Export, Partition, Tester
-from executorch.exir import CaptureConfig
+from executorch.backends.xnnpack.test.tester import Tester
 from torchvision.models.mobilenetv2 import MobileNet_V2_Weights
 
 
@@ -59,7 +55,7 @@ def test_qs8_mv2(self):
             .export()
             .to_edge()
             .check(list(ops_after_quantization))
-            .partition(Partition(partitioner=XnnpackQuantizedPartitioner))
+            .partition()
             .check(["torch.ops.executorch_call_delegate"])
             .check_not(list(ops_after_quantization))
             .to_executorch()