Skip ddp apply_optim_in_bwd tests for gloo (#1302)

To resolve https://ontrack-internal.amd.com/browse/SWDEV-403530 and https://ontrack-internal.amd.com/browse/SWDEV-419837. For more context check upstream issue pytorch#111834

Author: jataylo

torch/testing/_internal/distributed/distributed_test.py

@@ -4807,7 +4807,11 @@ def _test_ddp_apply_optim_in_backward(
                         # set_to_none for regular optimizer to match in backward
                         # case.
                         optim.zero_grad(set_to_none=True)
-
+        
+        @skip_but_pass_in_sandcastle_if(
+            BACKEND == "gloo" and HAS_TORCHVISION,
+            "Failing with gloo backend + torchvision due to ongoing issue https://github.com/pytorch/pytorch/issues/111834",
+        )
         @skip_if_lt_x_gpu(2)
         def test_ddp_apply_optim_in_backward(self):
             for optim_cls, init_before in itertools.product(
@@ -4820,6 +4824,10 @@ def test_ddp_apply_optim_in_backward(self):
                         init_before=init_before,
                     )
 
+        @skip_but_pass_in_sandcastle_if(
+            BACKEND == "gloo" and HAS_TORCHVISION,
+            "Failing with gloo backend + torchvision due to ongoing issue https://github.com/pytorch/pytorch/issues/111834",
+        )
         @skip_if_lt_x_gpu(2)
         def test_ddp_apply_optim_in_backward_grad_as_bucket_view_false(self):
             for init_before in [True, False]: