diff --git a/paddleslim/quant/quanter.py b/paddleslim/quant/quanter.py
index 95ee7a049edea4040de83fdc4398b8d4a685e8ad..328861720ba92e5742fa4ae9e70bc0c329a7acb3 100755
--- a/paddleslim/quant/quanter.py
+++ b/paddleslim/quant/quanter.py
@@ -185,7 +185,8 @@ def quant_aware(program,
                 weight_preprocess_func=None,
                 act_preprocess_func=None,
                 optimizer_func=None,
-                executor=None):
+                executor=None,
+                return_program=False):
     """Add quantization  and dequantization operators to "program" 
     for quantization training or testing.
 
@@ -226,6 +227,8 @@ def quant_aware(program,
             quantization function and preprocess function, this function must be set. Default is None.
         exe(Fluid.Executor): If user want to use self-defined quantization function and preprocess function, exe must be set for
                 initialization. Default is None.
+        return_program(bool): If user want return value is a Program rather than Compiled Program, This argument should be set True.
+                Default is False.
     Returns:
         fluid.CompiledProgram | fluid.Program: Program with quantization and dequantization ``operators``
     """
@@ -291,7 +294,7 @@ def quant_aware(program,
             VARS_MAPPING_TABLE))
         save_dict(main_graph.out_node_mapping_table)
 
-    if for_test:
+    if for_test or return_program:
         quant_program = main_graph.to_program()
     else:
         quant_program = fluid.CompiledProgram(main_graph.graph)