diff --git a/python/paddle/distributed/communication/all_gather.py b/python/paddle/distributed/communication/all_gather.py
index 47844cebdf02e6e85a13e9c941d6ce49e5da3562..90ff8ca14f92f51d4522bc702aff2cddd7e1bf10 100644
--- a/python/paddle/distributed/communication/all_gather.py
+++ b/python/paddle/distributed/communication/all_gather.py
@@ -51,19 +51,19 @@ def all_gather(tensor_list, tensor, group=None, sync_op=True):
     Examples:
         .. code-block:: python
 
-            # required: distributed
-            import paddle
-            import paddle.distributed as dist
-
-            dist.init_parallel_env()
-            tensor_list = []
-            if dist.get_rank() == 0:
-                data = paddle.to_tensor([[4, 5, 6], [4, 5, 6]])
-            else:
-                data = paddle.to_tensor([[1, 2, 3], [1, 2, 3]])
-            dist.all_gather(tensor_list, data)
-            print(tensor_list)
-            # [[[4, 5, 6], [4, 5, 6]], [[1, 2, 3], [1, 2, 3]]] (2 GPUs)
+            >>> # doctest: +REQUIRES(env: DISTRIBUTED)
+            >>> import paddle
+            >>> import paddle.distributed as dist
+
+            >>> dist.init_parallel_env()
+            >>> tensor_list = []
+            >>> if dist.get_rank() == 0:
+            ...     data = paddle.to_tensor([[4, 5, 6], [4, 5, 6]])
+            >>> else:
+            ...     data = paddle.to_tensor([[1, 2, 3], [1, 2, 3]])
+            >>> dist.all_gather(tensor_list, data)
+            >>> print(tensor_list)
+            [[[4, 5, 6], [4, 5, 6]], [[1, 2, 3], [1, 2, 3]]] (2 GPUs)
     """
     return stream.all_gather(tensor_list, tensor, group, sync_op)
 
@@ -87,19 +87,19 @@ def all_gather_object(object_list, obj, group=None):
     Examples:
         .. code-block:: python
 
-            # required: distributed
-            import paddle
-            import paddle.distributed as dist
-
-            dist.init_parallel_env()
-            object_list = []
-            if dist.get_rank() == 0:
-                obj = {"foo": [1, 2, 3]}
-            else:
-                obj = {"bar": [4, 5, 6]}
-            dist.all_gather_object(object_list, obj)
-            print(object_list)
-            # [{'foo': [1, 2, 3]}, {'bar': [4, 5, 6]}] (2 GPUs)
+            >>> # doctest: +REQUIRES(env: DISTRIBUTED)
+            >>> import paddle
+            >>> import paddle.distributed as dist
+
+            >>> dist.init_parallel_env()
+            >>> object_list = []
+            >>> if dist.get_rank() == 0:
+            ...     obj = {"foo": [1, 2, 3]}
+            >>> else:
+            ...     obj = {"bar": [4, 5, 6]}
+            >>> dist.all_gather_object(object_list, obj)
+            >>> print(object_list)
+            [{'foo': [1, 2, 3]}, {'bar': [4, 5, 6]}] (2 GPUs)
     """
     assert (
         framework.in_dynamic_mode()
diff --git a/python/paddle/distributed/communication/stream/all_gather.py b/python/paddle/distributed/communication/stream/all_gather.py
index 83cbe7ac1fcc139c45f5753c5e05a95d4c164c7b..fc814956be9983085ee9c7f1ce171c9c15d3f1b5 100644
--- a/python/paddle/distributed/communication/stream/all_gather.py
+++ b/python/paddle/distributed/communication/stream/all_gather.py
@@ -145,21 +145,21 @@ def all_gather(
     Examples:
         .. code-block:: python
 
-            # required: distributed
-            import paddle
-            import paddle.distributed as dist
-
-            dist.init_parallel_env()
-            local_rank = dist.get_rank()
-            tensor_list = []
-            if local_rank == 0:
-                data = paddle.to_tensor([[4, 5, 6], [4, 5, 6]])
-            else:
-                data = paddle.to_tensor([[1, 2, 3], [1, 2, 3]])
-            task = dist.stream.all_gather(tensor_list, data, sync_op=False)
-            task.wait()
-            print(tensor_list)
-            # [[[4, 5, 6], [4, 5, 6]], [[1, 2, 3], [1, 2, 3]]] (2 GPUs)
+            >>> # doctest: +REQUIRES(env: DISTRIBUTED)
+            >>> import paddle
+            >>> import paddle.distributed as dist
+
+            >>> dist.init_parallel_env()
+            >>> local_rank = dist.get_rank()
+            >>> tensor_list = []
+            >>> if local_rank == 0:
+            ...     data = paddle.to_tensor([[4, 5, 6], [4, 5, 6]])
+            >>> else:
+            ...     data = paddle.to_tensor([[1, 2, 3], [1, 2, 3]])
+            >>> task = dist.stream.all_gather(tensor_list, data, sync_op=False)
+            >>> task.wait()
+            >>> print(tensor_list)
+            [[[4, 5, 6], [4, 5, 6]], [[1, 2, 3], [1, 2, 3]]] (2 GPUs)
     """
     if group is not None and not group.is_member():
         raise RuntimeError(