Temporarily disable test_numerical_consistency_per_tensor (pytorch#30600)

Summary:
Pull Request resolved: pytorch#30600

test_numerical_consistency_per_tensor in test_fake_quant is failing on Windows.
ghstack-source-id: 94742124

Test Plan: CircleCI tests

Differential Revision: D18760287

fbshipit-source-id: 7f59355eab74e811bb370ad2836ed2f1def1f621

Author: jjlilley

test/test_fake_quant.py

@@ -107,6 +107,8 @@ def test_backward_per_tensor(self, device, X):
     @given(device=st.sampled_from(['cpu', 'cuda'] if torch.cuda.is_available() else ['cpu']),
            X=hu.tensor(shapes=hu.array_shapes(1, 5,),
                        qparams=hu.qparams(dtypes=torch.quint8)))
+    # https://github.com/pytorch/pytorch/issues/30604
+    @unittest.skip("temporarily disable the test")
     def test_numerical_consistency_per_tensor(self, device, X):
         r"""Comparing numerical consistency between CPU quantize/dequantize op and the CPU fake quantize op
         """