diff --git a/python/paddle/nn/functional/activation.py b/python/paddle/nn/functional/activation.py
index 0ec80b3c5bb931e06431fd581f60682fb3d4ad61..4dc3e3a62ec5d9b78c95feb231b0d468ec7e55bf 100644
--- a/python/paddle/nn/functional/activation.py
+++ b/python/paddle/nn/functional/activation.py
@@ -1110,15 +1110,15 @@ def softmax(x, axis=-1, dtype=None, name=None):
         use_cudnn = True
         if dtype is None:
             check_variable_and_dtype(
-                x, 'x', ['float16', 'float32', 'float64'], 'softmax'
+                x, 'x', ['float16', 'bfloat16', 'float32', 'float64'], 'softmax'
             )
         else:
             check_dtype(
                 dtype,
                 'dtype',
-                ['float32', 'float64'],
+                ['float16', 'bfloat16', 'float32', 'float64'],
                 'softmax',
-                'If dtype is not None, it only support float32 or float64.',
+                'If dtype is not None, it only support float16, bfloat16, float32 or float64.',
             )
 
         helper = LayerHelper("softmax", **locals())
diff --git a/python/paddle/nn/layer/activation.py b/python/paddle/nn/layer/activation.py
index ebe305d7869d1cdbf9e81c8daa59c815cd8aa3f3..6c85ae646b71c8af713d46c210dc805034d17754 100644
--- a/python/paddle/nn/layer/activation.py
+++ b/python/paddle/nn/layer/activation.py
@@ -1324,7 +1324,7 @@ class Softmax(Layer):
         self._name = name
 
     def forward(self, x):
-        return F.softmax(x, self._axis, self._dtype, self._name)
+        return F.softmax(x, self._axis, name=self._name)
 
     def extra_repr(self):
         name_str = ', name={}'.format(self._name) if self._name else ''