diff --git a/README.md b/README.md
index 1818ddd61cc5423c4a590815930d007303f18e81..afbfd208404bef99f51951b25108fbd17d5ae0be 100644
--- a/README.md
+++ b/README.md
@@ -111,9 +111,9 @@ python -m paddle_serving_server.serve --model uci_housing_model --thread 10 --po
 | `port` | int | `9292` | Exposed port of current service to users|
 | `name` | str | `""` | Service name, can be used to generate HTTP request url |
 | `model` | str | `""` | Path of paddle model directory to be served |
-| `mem_optim` | bool | `False` | Enable memory / graphic memory optimization |
-| `ir_optim` | bool | `False` | Enable analysis and optimization of calculation graph |
-| `use_mkl` (Only for cpu version) | bool | `False` | Run inference with MKL |
+| `mem_optim` | - | - | Enable memory / graphic memory optimization |
+| `ir_optim` | - | - | Enable analysis and optimization of calculation graph |
+| `use_mkl` (Only for cpu version) | - | - | Run inference with MKL |
 
 Here, we use `curl` to send a HTTP POST request to the service we just started. Users can use any python library to send HTTP POST as well, e.g, [requests](https://requests.readthedocs.io/en/master/).
 </center>
diff --git a/README_CN.md b/README_CN.md
index 29cf095248f4c125b3dba7146e67efe8b7abae6c..24104f3c48f65d86845b0937650bf82600383eff 100644
--- a/README_CN.md
+++ b/README_CN.md
@@ -115,9 +115,9 @@ python -m paddle_serving_server.serve --model uci_housing_model --thread 10 --po
 | `port` | int | `9292` | Exposed port of current service to users|
 | `name` | str | `""` | Service name, can be used to generate HTTP request url |
 | `model` | str | `""` | Path of paddle model directory to be served |
-| `mem_optim` | bool | `False` | Enable memory optimization |
-| `ir_optim` | bool | `False` | Enable analysis and optimization of calculation graph |
-| `use_mkl` (Only for cpu version) | bool | `False` | Run inference with MKL |
+| `mem_optim` | - | - | Enable memory optimization |
+| `ir_optim` | - | - | Enable analysis and optimization of calculation graph |
+| `use_mkl` (Only for cpu version) | - | - | Run inference with MKL |
 
 我们使用 `curl` 命令来发送HTTP POST请求给刚刚启动的服务。用户也可以调用python库来发送HTTP POST请求，请参考英文文档 [requests](https://requests.readthedocs.io/en/master/)。
 </center>
diff --git a/doc/BERT_10_MINS.md b/doc/BERT_10_MINS.md
index 71f6f065f4101aae01e077910fc5b6bd6b039b46..53e51768d3eaee6a1faac8d9ae2c62e7f1aa63ee 100644
--- a/doc/BERT_10_MINS.md
+++ b/doc/BERT_10_MINS.md
@@ -59,7 +59,7 @@ the script of client side bert_client.py is as follow:
 import os
 import sys
 from paddle_serving_client import Client
-from paddle_serving_app import ChineseBertReader
+from paddle_serving_app.reader import ChineseBertReader
 
 reader = ChineseBertReader()
 fetch = ["pooled_output"]
diff --git a/doc/BERT_10_MINS_CN.md b/doc/BERT_10_MINS_CN.md
index b7a5180da1bae2dafc431251f2b98c8a2041856a..e4904d86b6a056ba74b6ed85b47745575b749279 100644
--- a/doc/BERT_10_MINS_CN.md
+++ b/doc/BERT_10_MINS_CN.md
@@ -52,7 +52,7 @@ pip install paddle_serving_app
 ``` python
 import sys
 from paddle_serving_client import Client
-from paddle_serving_app import ChineseBertReader
+from paddle_serving_app.reader import ChineseBertReader
 
 reader = ChineseBertReader()
 fetch = ["pooled_output"]
diff --git a/python/paddle_serving_server/serve.py b/python/paddle_serving_server/serve.py
index 894b0c5b132845cbde589982e1fb471f028e820b..e75240dfafd436e5557a8f11396029e6be5868fe 100644
--- a/python/paddle_serving_server/serve.py
+++ b/python/paddle_serving_server/serve.py
@@ -40,10 +40,14 @@ def parse_args():  # pylint: disable=doc-string-missing
     parser.add_argument(
         "--device", type=str, default="cpu", help="Type of device")
     parser.add_argument(
-        "--mem_optim", type=bool, default=False, help="Memory optimize")
+        "--mem_optim",
+        default=False,
+        action="store_true",
+        help="Memory optimize")
     parser.add_argument(
-        "--ir_optim", type=bool, default=False, help="Graph optimize")
-    parser.add_argument("--use_mkl", type=bool, default=False, help="Use MKL")
+        "--ir_optim", default=False, action="store_true", help="Graph optimize")
+    parser.add_argument(
+        "--use_mkl", default=False, action="store_true", help="Use MKL")
     parser.add_argument(
         "--max_body_size",
         type=int,
diff --git a/python/paddle_serving_server_gpu/__init__.py b/python/paddle_serving_server_gpu/__init__.py
index e40c0fa48763eaa66373e9f2149552c4f8693eb7..ace4905536e9c9a71d76d41da6836966986910a2 100644
--- a/python/paddle_serving_server_gpu/__init__.py
+++ b/python/paddle_serving_server_gpu/__init__.py
@@ -47,9 +47,12 @@ def serve_args():
     parser.add_argument(
         "--name", type=str, default="None", help="Default service name")
     parser.add_argument(
-        "--mem_optim", type=bool, default=False, help="Memory optimize")
+        "--mem_optim",
+        default=False,
+        action="store_true",
+        help="Memory optimize")
     parser.add_argument(
-        "--ir_optim", type=bool, default=False, help="Graph optimize")
+        "--ir_optim", default=False, action="store_true", help="Graph optimize")
     parser.add_argument(
         "--max_body_size",
         type=int,