diff --git a/python/paddle/fluid/tests/unittests/test_broadcast_to_op.py b/python/paddle/fluid/tests/unittests/test_broadcast_to_op.py
index 897c5b54b169b7e6054cf6692b951f4d8d234ecc..18daf2059f2410c029aa423dad08051dc72f5100 100644
--- a/python/paddle/fluid/tests/unittests/test_broadcast_to_op.py
+++ b/python/paddle/fluid/tests/unittests/test_broadcast_to_op.py
@@ -70,6 +70,41 @@ class TestBroadcastToAPI(unittest.TestCase):
         assert np.array_equal(res_2, np.tile(input, (1, 1)))
         assert np.array_equal(res_3, np.tile(input, (1, 1)))
 
+    def test_api_fp16_gpu(self):
+        if paddle.fluid.core.is_compiled_with_cuda():
+            place = paddle.CUDAPlace(0)
+            with paddle.static.program_guard(
+                paddle.static.Program(), paddle.static.Program()
+            ):
+                input = np.random.random([12, 14]).astype("float16")
+                x = paddle.static.data(
+                    name="x", shape=[12, 14], dtype="float16"
+                )
+
+                positive_2 = paddle.fluid.layers.fill_constant([1], "int32", 12)
+                expand_shape = paddle.static.data(
+                    name="expand_shape",
+                    shape=[2],
+                    dtype="int32",
+                )
+
+                out_1 = paddle.broadcast_to(x, shape=[12, 14])
+                out_2 = paddle.broadcast_to(x, shape=[positive_2, 14])
+                out_3 = paddle.broadcast_to(x, shape=expand_shape)
+
+                exe = paddle.static.Executor(place)
+                res_1, res_2, res_3 = exe.run(
+                    paddle.static.default_main_program(),
+                    feed={
+                        "x": input,
+                        "expand_shape": np.array([12, 14]).astype("int32"),
+                    },
+                    fetch_list=[out_1, out_2, out_3],
+                )
+                assert np.array_equal(res_1, np.tile(input, (1, 1)))
+                assert np.array_equal(res_2, np.tile(input, (1, 1)))
+                assert np.array_equal(res_3, np.tile(input, (1, 1)))
+
 
 if __name__ == "__main__":
     unittest.main()
diff --git a/python/paddle/tensor/manipulation.py b/python/paddle/tensor/manipulation.py
index e2325fda753a1aae749988429b7a10acf1520ff2..8f257725e89bed55b991dd0674b520326a6a732e 100644
--- a/python/paddle/tensor/manipulation.py
+++ b/python/paddle/tensor/manipulation.py
@@ -3256,7 +3256,7 @@ def broadcast_to(x, shape, name=None):
 
 
     Args:
-        x (Tensor): The input tensor, its data type is bool, float32, float64, int32 or int64.
+        x (Tensor): The input tensor, its data type is bool, float16, float32, float64, int32 or int64.
         shape (list|tuple|Tensor): The result shape after broadcasting. The data type is int32. If shape is a list or tuple, all its elements
             should be integers or 0-D or 1-D Tensors with the data type int32. If shape is a Tensor, it should be an 1-D Tensor with the data type int32.
             The value -1 in shape means keeping the corresponding dimension unchanged.