From 0f1d47d15aeec56b0d32b1d2bda8ef161ce1ffb1 Mon Sep 17 00:00:00 2001
From: Dmitry Nikolaev <139769634+dnikolaev-amd@users.noreply.github.com>
Date: Thu, 9 Jan 2025 03:48:21 +0100
Subject: [PATCH] [rocm6.4_internal_testing] remove xfail from
 'batch_norm_with_update' (#1821)

remove `xfail` from `batch_norm_with_update` op in `test_grad` and
`test_vmap_autograd_grad`
these tests are passed now
Fixes https://ontrack-internal.amd.com/browse/SWDEV-472564
cherry-picked from rocm6.3_internal_testing PR
https://github.com/ROCm/pytorch/pull/1776
---
 test/functorch/test_ops.py | 14 --------------
 1 file changed, 14 deletions(-)

diff --git a/test/functorch/test_ops.py b/test/functorch/test_ops.py
index 84c655d348c778..632437e0bdb39f 100644
--- a/test/functorch/test_ops.py
+++ b/test/functorch/test_ops.py
@@ -438,13 +438,6 @@ class TestOperators(TestCase):
                 ),  # Works on ROCm
                 xfail("torch.ops.aten._flash_attention_forward"),
                 xfail("torch.ops.aten._efficient_attention_forward"),
-                # RuntimeError: Expected contiguous tensor, but got
-                # non-contiguous tensor for argument #2 'grad_output'
-                decorate(
-                    "_batch_norm_with_update",
-                    decorator=expectedFailureIf(TEST_WITH_ROCM),
-                    device_type="cuda",
-                ),
             }
         ),
     )
@@ -2394,13 +2387,6 @@ def fn(input, weight, bias):
             skip("sparse.sampled_addmm", ""),
             skip("sparse.mm", "reduce"),
             skip("native_layer_norm", "", device_type="cpu"),
-            # RuntimeError: Expected contiguous tensor, but got
-            # non-contiguous tensor for argument #2 'grad_output'
-            decorate(
-                "_batch_norm_with_update",
-                decorator=expectedFailureIf(TEST_WITH_ROCM),
-                device_type="cuda",
-            ),
         },
     )
     @opsToleranceOverride(