rename paddle_serving_server_gpu

python/examples/bert/README.md

@@ -48,7 +48,7 @@ python -m paddle_serving_server.serve --model bert_seq128_model/ --port 9292  #c
 ```
 Or,start gpu inference service,Run
 ```
-python -m paddle_serving_server_gpu.serve --model bert_seq128_model/ --port 9292 --gpu_ids 0 #launch gpu inference service at GPU 0
+python -m paddle_serving_server.serve --model bert_seq128_model/ --port 9292 --gpu_ids 0 #launch gpu inference service at GPU 0
 ```
 
 ### RPC Inference

python/examples/bert/README_CN.md

@@ -45,7 +45,7 @@ python -m paddle_serving_server.serve --model bert_seq128_model/ --port 9292  #
 ```
 或者，启动gpu预测服务，执行
 ```
-python -m paddle_serving_server_gpu.serve --model bert_seq128_model/ --port 9292 --gpu_ids 0 #在gpu 0上启动gpu预测服务
+python -m paddle_serving_server.serve --model bert_seq128_model/ --port 9292 --gpu_ids 0 #在gpu 0上启动gpu预测服务
 
 ```
 

python/examples/bert/benchmark.sh

@@ -12,7 +12,7 @@ else
     mkdir utilization
 fi
 #start server
-$PYTHONROOT/bin/python3 -m paddle_serving_server_gpu.serve --model $1 --port 9292 --thread 4 --gpu_ids 0,1,2,3 --mem_optim  --ir_optim >  elog  2>&1 &
+$PYTHONROOT/bin/python3 -m paddle_serving_server.serve --model $1 --port 9292 --thread 4 --gpu_ids 0,1,2,3 --mem_optim  --ir_optim >  elog  2>&1 &
 sleep 5
 
 #warm up

python/examples/bert/benchmark_with_profile.sh

 export CUDA_VISIBLE_DEVICES=0,1,2,3
-python -m paddle_serving_server_gpu.serve --model bert_seq20_model/ --port 9295 --thread 4 --gpu_ids 0,1,2,3 2> elog > stdlog &
+python -m paddle_serving_server.serve --model bert_seq20_model/ --port 9295 --thread 4 --gpu_ids 0,1,2,3 2> elog > stdlog &
 export FLAGS_profile_client=1
 export FLAGS_profile_server=1
 sleep 5

python/examples/bert/bert_gpu_server.py

@@ -14,9 +14,9 @@
 
 import os
 import sys
-from paddle_serving_server_gpu import OpMaker
-from paddle_serving_server_gpu import OpSeqMaker
-from paddle_serving_server_gpu import Server
+from paddle_serving_server import OpMaker
+from paddle_serving_server import OpSeqMaker
+from paddle_serving_server import Server
 
 op_maker = OpMaker()
 read_op = op_maker.create('general_reader')

python/examples/bert/bert_web_service_gpu.py

@@ -13,7 +13,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 # pylint: disable=doc-string-missing
-from paddle_serving_server_gpu.web_service import WebService
+from paddle_serving_server.web_service import WebService
 from paddle_serving_app.reader import ChineseBertReader
 import sys
 import os

python/examples/cascade_rcnn/README.md

@@ -10,7 +10,7 @@ If you want to have more detection models, please refer to [Paddle Detection Mod
 
 ### Start the service
 ```
-python -m paddle_serving_server_gpu.serve --model serving_server --port 9292 --gpu_id 0
+python -m paddle_serving_server.serve --model serving_server --port 9292 --gpu_id 0
 ```
 
 ### Perform prediction

python/examples/cascade_rcnn/README_CN.md

@@ -10,7 +10,7 @@ sh get_data.sh
 
 ### 启动服务
 ```
-python -m paddle_serving_server_gpu.serve --model serving_server --port 9292 --gpu_id 0
+python -m paddle_serving_server.serve --model serving_server --port 9292 --gpu_id 0
 ```
 
 ### 执行预测

python/examples/criteo_ctr/README.md

@@ -20,7 +20,7 @@ the directories like `ctr_serving_model` and `ctr_client_conf` will appear.
 
 ```
 python -m paddle_serving_server.serve --model ctr_serving_model/ --port 9292 #CPU RPC Service
-python -m paddle_serving_server_gpu.serve --model ctr_serving_model/ --port 9292 --gpu_ids 0 #RPC Service on GPU 0
+python -m paddle_serving_server.serve --model ctr_serving_model/ --port 9292 --gpu_ids 0 #RPC Service on GPU 0
 ```
 
 ### RPC Infer

python/examples/criteo_ctr/README_CN.md

@@ -20,7 +20,7 @@ mv models/ctr_serving_model .
 
 ```
 python -m paddle_serving_server.serve --model ctr_serving_model/ --port 9292 #启动CPU预测服务
-python -m paddle_serving_server_gpu.serve --model ctr_serving_model/ --port 9292 --gpu_ids 0 #在GPU 0上启动预测服务
+python -m paddle_serving_server.serve --model ctr_serving_model/ --port 9292 --gpu_ids 0 #在GPU 0上启动预测服务
 ```
 
 ### 执行预测

python/examples/deeplabv3/README.md

@@ -12,7 +12,7 @@ tar -xzvf deeplabv3.tar.gz
 ### Start Service
 
 ```
-python -m paddle_serving_server_gpu.serve --model deeplabv3_server --gpu_ids 0 --port 9494
+python -m paddle_serving_server.serve --model deeplabv3_server --gpu_ids 0 --port 9494
 ```
 
 ### Client Prediction

python/examples/deeplabv3/README_CN.md

@@ -12,7 +12,7 @@ tar -xzvf deeplabv3.tar.gz
 ### 启动服务端
 
 ```
-python -m paddle_serving_server_gpu.serve --model deeplabv3_server --gpu_ids 0 --port 9494
+python -m paddle_serving_server.serve --model deeplabv3_server --gpu_ids 0 --port 9494
 ```
 
 ### 客户端预测

python/examples/detection/faster_rcnn_r50_fpn_1x_coco/README.md

@@ -10,7 +10,7 @@ wget --no-check-certificate https://paddle-serving.bj.bcebos.com/pddet_demo/2.0/
 ### Start the service
 ```
 tar xf faster_rcnn_r50_fpn_1x_coco.tar
-python -m paddle_serving_server_gpu.serve --model serving_server --port 9494 --gpu_ids 0
+python -m paddle_serving_server.serve --model serving_server --port 9494 --gpu_ids 0
 ```
 
 This model support TensorRT, if you want a faster inference, please use `--use_trt`. 

python/examples/detection/faster_rcnn_r50_fpn_1x_coco/README_CN.md

@@ -11,7 +11,7 @@ wget --no-check-certificate https://paddle-serving.bj.bcebos.com/pddet_demo/2.0/
 ### 启动服务
 ```
 tar xf faster_rcnn_r50_fpn_1x_coco.tar
-python -m paddle_serving_server_gpu.serve --model serving_server --port 9494 --gpu_ids 0
+python -m paddle_serving_server.serve --model serving_server --port 9494 --gpu_ids 0
 ```
 该模型支持TensorRT，如果想要更快的预测速度，可以开启`--use_trt`选项。
 

python/examples/detection/ppyolo_r50vd_dcn_1x_coco/README.md

@@ -10,7 +10,7 @@ wget --no-check-certificate https://paddle-serving.bj.bcebos.com/pddet_demo/2.0/
 ### Start the service
 ```
 tar xf ppyolo_r50vd_dcn_1x_coco.tar
-python -m paddle_serving_server_gpu.serve --model serving_server --port 9494 --gpu_ids 0
+python -m paddle_serving_server.serve --model serving_server --port 9494 --gpu_ids 0
 ```
 
 This model support TensorRT, if you want a faster inference, please use `--use_trt`.

python/examples/detection/ppyolo_r50vd_dcn_1x_coco/README_CN.md

@@ -11,7 +11,7 @@ wget --no-check-certificate https://paddle-serving.bj.bcebos.com/pddet_demo/2.0/
 ### 启动服务
 ```
 tar xf ppyolo_r50vd_dcn_1x_coco.tar
-python -m paddle_serving_server_gpu.serve --model serving_server --port 9494 --gpu_ids 0
+python -m paddle_serving_server.serve --model serving_server --port 9494 --gpu_ids 0
 ```
 
 该模型支持TensorRT，如果想要更快的预测速度，可以开启`--use_trt`选项。

python/examples/detection/ttfnet_darknet53_1x_coco/README.md

@@ -10,7 +10,7 @@ wget --no-check-certificate https://paddle-serving.bj.bcebos.com/pddet_demo/2.0/
 ### Start the service
 ```
 tar xf ttfnet_darknet53_1x_coco.tar
-python -m paddle_serving_server_gpu.serve --model serving_server --port 9494 --gpu_ids 0
+python -m paddle_serving_server.serve --model serving_server --port 9494 --gpu_ids 0
 ```
 This model support TensorRT, if you want a faster inference, please use `--use_trt`.
 

python/examples/detection/ttfnet_darknet53_1x_coco/README_CN.md

@@ -11,7 +11,7 @@ wget --no-check-certificate https://paddle-serving.bj.bcebos.com/pddet_demo/2.0/
 ### 启动服务
 ```
 tar xf ttfnet_darknet53_1x_coco.tar
-python -m paddle_serving_server_gpu.serve --model serving_server --port 9494 --gpu_ids 0
+python -m paddle_serving_server.serve --model serving_server --port 9494 --gpu_ids 0
 ```
 
 该模型支持TensorRT，如果想要更快的预测速度，可以开启`--use_trt`选项。

python/examples/detection/yolov3_darknet53_270e_coco/README.md

@@ -10,7 +10,7 @@ wget --no-check-certificate https://paddle-serving.bj.bcebos.com/pddet_demo/2.0/
 ### Start the service
 ```
 tar xf yolov3_darknet53_270e_coco.tar
-python -m paddle_serving_server_gpu.serve --model serving_server --port 9494 --gpu_ids 0
+python -m paddle_serving_server.serve --model serving_server --port 9494 --gpu_ids 0
 ```
 
 This model support TensorRT, if you want a faster inference, please use `--use_trt`.

python/examples/detection/yolov3_darknet53_270e_coco/README_CN.md

@@ -11,7 +11,7 @@ wget --no-check-certificate https://paddle-serving.bj.bcebos.com/pddet_demo/2.0/
 ### 启动服务
 ```
 tar xf yolov3_darknet53_270e_coco.tar
-python -m paddle_serving_server_gpu.serve --model serving_server --port 9494 --gpu_ids 0
+python -m paddle_serving_server.serve --model serving_server --port 9494 --gpu_ids 0
 ```
 
 该模型支持TensorRT，如果想要更快的预测速度，可以开启`--use_trt`选项。

python/examples/encryption/README.md

@@ -26,7 +26,7 @@ python -m paddle_serving_server.serve --model encrypt_server/ --port 9300 --use_
 ```
 GPU Service
 ```
-python -m paddle_serving_server_gpu.serve --model encrypt_server/ --port 9300 --use_encryption_model --gpu_ids 0
+python -m paddle_serving_server.serve --model encrypt_server/ --port 9300 --use_encryption_model --gpu_ids 0
 ```
 
 ## Prediction

python/examples/encryption/README_CN.md

@@ -24,7 +24,7 @@ python -m paddle_serving_server.serve --model encrypt_server/ --port 9300 --use_
 ```
 GPU预测服务
 ```
-python -m paddle_serving_server_gpu.serve --model encrypt_server/ --port 9300 --use_encryption_model --gpu_ids 0
+python -m paddle_serving_server.serve --model encrypt_server/ --port 9300 --use_encryption_model --gpu_ids 0
 ```
 
 ## 预测

python/examples/grpc_impl_example/fit_a_line/test_server_gpu.py

@@ -15,9 +15,9 @@
 
 import os
 import sys
-from paddle_serving_server_gpu import OpMaker
-from paddle_serving_server_gpu import OpSeqMaker
-from paddle_serving_server_gpu import MultiLangServer as Server
+from paddle_serving_server import OpMaker
+from paddle_serving_server import OpSeqMaker
+from paddle_serving_server import MultiLangServer as Server
 
 op_maker = OpMaker()
 read_op = op_maker.create('general_reader')

python/examples/grpc_impl_example/yolov4/README.md

@@ -12,7 +12,7 @@ tar -xzvf yolov4.tar.gz
 ## Start RPC Service
 
 ```
-python -m paddle_serving_server_gpu.serve --model yolov4_model --port 9393 --gpu_ids 0 --use_multilang
+python -m paddle_serving_server.serve --model yolov4_model --port 9393 --gpu_ids 0 --use_multilang
 ```
 
 ## Prediction

python/examples/grpc_impl_example/yolov4/README_CN.md

@@ -12,7 +12,7 @@ tar -xzvf yolov4.tar.gz
 ## 启动RPC服务
 
 ```
-python -m paddle_serving_server_gpu.serve --model yolov4_model --port 9393 --gpu_ids 0 --use_multilang
+python -m paddle_serving_server.serve --model yolov4_model --port 9393 --gpu_ids 0 --use_multilang
 ```
 
 ## 预测

python/examples/imagenet/README.md

@@ -39,7 +39,7 @@ python -m paddle_serving_server.serve --model ResNet50_vd_model --port 9696 #cpu
 ```
 
 ```
-python -m paddle_serving_server_gpu.serve --model ResNet50_vd_model --port 9696 --gpu_ids 0 #gpu inference service
+python -m paddle_serving_server.serve --model ResNet50_vd_model --port 9696 --gpu_ids 0 #gpu inference service
 ```
 
 client send inference request

python/examples/imagenet/README_CN.md

@@ -39,7 +39,7 @@ python -m paddle_serving_server.serve --model ResNet50_vd_model --port 9696 #cpu
 ```
 
 ```
-python -m paddle_serving_server_gpu.serve --model ResNet50_vd_model --port 9696 --gpu_ids 0 #gpu预测服务
+python -m paddle_serving_server.serve --model ResNet50_vd_model --port 9696 --gpu_ids 0 #gpu预测服务
 ```
 
 client端进行预测

python/examples/imagenet/benchmark.sh

@@ -2,7 +2,7 @@ rm profile_log*
 export CUDA_VISIBLE_DEVICES=0,1,2,3
 export FLAGS_profile_server=1
 export FLAGS_profile_client=1
-python -m paddle_serving_server_gpu.serve --model $1 --port 9292 --thread 4 --gpu_ids 0,1,2,3 --mem_optim --ir_optim  2> elog > stdlog &
+python -m paddle_serving_server.serve --model $1 --port 9292 --thread 4 --gpu_ids 0,1,2,3 --mem_optim --ir_optim  2> elog > stdlog &
 
 sleep 5
 gpu_id=0

python/examples/imagenet/resnet50_web_service.py

@@ -25,7 +25,7 @@ device = sys.argv[2]
 if device == "cpu":
     from paddle_serving_server.web_service import WebService
 else:
-    from paddle_serving_server_gpu.web_service import WebService
+    from paddle_serving_server.web_service import WebService
 
 
 class ImageService(WebService):

python/examples/mobilenet/README.md

@@ -12,7 +12,7 @@ tar -xzvf mobilenet_v2_imagenet.tar.gz
 ### Start Service
 
 ```
-python -m paddle_serving_server_gpu.serve --model mobilenet_v2_imagenet_model --gpu_ids 0 --port 9393
+python -m paddle_serving_server.serve --model mobilenet_v2_imagenet_model --gpu_ids 0 --port 9393
 ```
 
 ### Client Prediction

python/examples/mobilenet/README_CN.md

@@ -12,7 +12,7 @@ tar -xzvf mobilenet_v2_imagenet.tar.gz
 ### 启动服务端
 
 ```
-python -m paddle_serving_server_gpu.serve --model mobilenet_v2_imagenet_model --gpu_ids 0 --port 9393
+python -m paddle_serving_server.serve --model mobilenet_v2_imagenet_model --gpu_ids 0 --port 9393
 ```
 
 ### 客户端预测

python/examples/ocr/README.md

@@ -26,7 +26,7 @@ tar xf test_imgs.tar
 python -m paddle_serving_server.serve --model ocr_det_model --port 9293
 python ocr_web_server.py cpu
 #for gpu user
-python -m paddle_serving_server_gpu.serve --model ocr_det_model --port 9293 --gpu_id 0
+python -m paddle_serving_server.serve --model ocr_det_model --port 9293 --gpu_id 0
 python ocr_web_server.py gpu
 ```
 

python/examples/ocr/README_CN.md

@@ -25,7 +25,7 @@ tar xf test_imgs.tar
 python -m paddle_serving_server.serve --model ocr_det_model --port 9293
 python ocr_web_server.py cpu
 #for gpu user
-python -m paddle_serving_server_gpu.serve --model ocr_det_model --port 9293 --gpu_id 0
+python -m paddle_serving_server.serve --model ocr_det_model --port 9293 --gpu_id 0
 python ocr_web_server.py gpu
 ```
 

python/examples/ocr/det_debugger_server.py

@@ -22,7 +22,7 @@ from paddle_serving_app.reader import Sequential, ResizeByFactor
 from paddle_serving_app.reader import Div, Normalize, Transpose
 from paddle_serving_app.reader import DBPostProcess, FilterBoxes
 if sys.argv[1] == 'gpu':
-    from paddle_serving_server_gpu.web_service import WebService
+    from paddle_serving_server.web_service import WebService
 elif sys.argv[1] == 'cpu':
     from paddle_serving_server.web_service import WebService
 import time

python/examples/ocr/det_web_server.py

@@ -22,7 +22,7 @@ from paddle_serving_app.reader import Sequential, ResizeByFactor
 from paddle_serving_app.reader import Div, Normalize, Transpose
 from paddle_serving_app.reader import DBPostProcess, FilterBoxes
 if sys.argv[1] == 'gpu':
-    from paddle_serving_server_gpu.web_service import WebService
+    from paddle_serving_server.web_service import WebService
 elif sys.argv[1] == 'cpu':
     from paddle_serving_server.web_service import WebService
 import time

python/examples/ocr/ocr_debugger_server.py

@@ -23,7 +23,7 @@ from paddle_serving_app.reader import Sequential, URL2Image, ResizeByFactor
 from paddle_serving_app.reader import Div, Normalize, Transpose
 from paddle_serving_app.reader import DBPostProcess, FilterBoxes, GetRotateCropImage, SortedBoxes
 if sys.argv[1] == 'gpu':
-    from paddle_serving_server_gpu.web_service import WebService
+    from paddle_serving_server.web_service import WebService
 elif sys.argv[1] == 'cpu':
     from paddle_serving_server.web_service import WebService
 from paddle_serving_app.local_predict import LocalPredictor

python/examples/ocr/ocr_web_server.py

@@ -23,7 +23,7 @@ from paddle_serving_app.reader import Sequential, URL2Image, ResizeByFactor
 from paddle_serving_app.reader import Div, Normalize, Transpose
 from paddle_serving_app.reader import DBPostProcess, FilterBoxes, GetRotateCropImage, SortedBoxes
 if sys.argv[1] == 'gpu':
-    from paddle_serving_server_gpu.web_service import WebService
+    from paddle_serving_server.web_service import WebService
 elif sys.argv[1] == 'cpu':
     from paddle_serving_server.web_service import WebService
 import time

python/examples/ocr/rec_debugger_server.py

@@ -23,7 +23,7 @@ from paddle_serving_app.reader import Sequential, URL2Image, ResizeByFactor
 from paddle_serving_app.reader import Div, Normalize, Transpose
 from paddle_serving_app.reader import DBPostProcess, FilterBoxes, GetRotateCropImage, SortedBoxes
 if sys.argv[1] == 'gpu':
-    from paddle_serving_server_gpu.web_service import WebService
+    from paddle_serving_server.web_service import WebService
 elif sys.argv[1] == 'cpu':
     from paddle_serving_server.web_service import WebService
 import time

python/examples/ocr/rec_web_server.py

@@ -23,7 +23,7 @@ from paddle_serving_app.reader import Sequential, URL2Image, ResizeByFactor
 from paddle_serving_app.reader import Div, Normalize, Transpose
 from paddle_serving_app.reader import DBPostProcess, FilterBoxes, GetRotateCropImage, SortedBoxes
 if sys.argv[1] == 'gpu':
-    from paddle_serving_server_gpu.web_service import WebService
+    from paddle_serving_server.web_service import WebService
 elif sys.argv[1] == 'cpu':
     from paddle_serving_server.web_service import WebService
 import time

python/examples/pipeline/imagenet/pipeline_rpc_client.py

@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 try:
-    from paddle_serving_server_gpu.pipeline import PipelineClient
+    from paddle_serving_server.pipeline import PipelineClient
 except ImportError:
     from paddle_serving_server.pipeline import PipelineClient
 import numpy as np

python/examples/pipeline/imagenet/resnet50_web_service.py

@@ -14,7 +14,7 @@
 import sys
 from paddle_serving_app.reader import Sequential, URL2Image, Resize, CenterCrop, RGB2BGR, Transpose, Div, Normalize, Base64ToImage
 try:
-    from paddle_serving_server_gpu.web_service import WebService, Op
+    from paddle_serving_server.web_service import WebService, Op
 except ImportError:
     from paddle_serving_server.web_service import WebService, Op
 import logging

python/examples/pipeline/imdb_model_ensemble/test_pipeline_server.py

@@ -22,7 +22,7 @@ import logging
 try:
     from paddle_serving_server.web_service import WebService
 except ImportError:
-    from paddle_serving_server_gpu.web_service import WebService
+    from paddle_serving_server.web_service import WebService
 
 _LOGGER = logging.getLogger()
 user_handler = logging.StreamHandler()

python/examples/pipeline/ocr/pipeline_rpc_client.py

@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 try:
-    from paddle_serving_server_gpu.pipeline import PipelineClient
+    from paddle_serving_server.pipeline import PipelineClient
 except ImportError:
     from paddle_serving_server.pipeline import PipelineClient
 import numpy as np

python/examples/pipeline/ocr/web_service.py

@@ -14,7 +14,7 @@
 try:
     from paddle_serving_server.web_service import WebService, Op
 except ImportError:
-    from paddle_serving_server_gpu.web_service import WebService, Op
+    from paddle_serving_server.web_service import WebService, Op
 import logging
 import numpy as np
 import cv2

python/examples/pipeline/simple_web_service/web_service.py

@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 try:
-    from paddle_serving_server_gpu.web_service import WebService, Op
+    from paddle_serving_server.web_service import WebService, Op
 except ImportError:
     from paddle_serving_server.web_service import WebService, Op
 import logging

python/examples/resnet_v2_50/README.md

@@ -12,7 +12,7 @@ tar -xzvf resnet_v2_50_imagenet.tar.gz
 ### Start Service
 
 ```
-python -m paddle_serving_server_gpu.serve --model resnet_v2_50_imagenet_model --gpu_ids 0 --port 9393
+python -m paddle_serving_server.serve --model resnet_v2_50_imagenet_model --gpu_ids 0 --port 9393
 ```
 
 ### Client Prediction

python/examples/resnet_v2_50/README_CN.md

@@ -12,7 +12,7 @@ tar -xzvf resnet_v2_50_imagenet.tar.gz
 ### 启动服务端
 
 ```
-python -m paddle_serving_server_gpu.serve --model resnet_v2_50_imagenet_model --gpu_ids 0 --port 9393
+python -m paddle_serving_server.serve --model resnet_v2_50_imagenet_model --gpu_ids 0 --port 9393
 ```
 
 ### 客户端预测

python/examples/unet_for_image_seg/README.md

@@ -12,7 +12,7 @@ tar -xzvf unet.tar.gz
 ### Start Service
 
 ```
-python -m paddle_serving_server_gpu.serve --model unet_model --gpu_ids 0 --port 9494
+python -m paddle_serving_server.serve --model unet_model --gpu_ids 0 --port 9494
 ```
 
 ### Client Prediction

python/examples/unet_for_image_seg/README_CN.md

@@ -12,7 +12,7 @@ tar -xzvf unet.tar.gz
 ### 启动服务端
 
 ```
-python -m paddle_serving_server_gpu.serve --model unet_model --gpu_ids 0 --port 9494
+python -m paddle_serving_server.serve --model unet_model --gpu_ids 0 --port 9494
 ```
 
 ### 客户端预测

python/examples/xpu/fit_a_line_xpu/README.md

@@ -15,7 +15,7 @@ sh get_data.sh
 ### Start server
 
 ```shell
-python -m paddle_serving_server_gpu.serve --model uci_housing_model --thread 10 --port 9393 --use_lite --use_xpu --ir_optim
+python -m paddle_serving_server.serve --model uci_housing_model --thread 10 --port 9393 --use_lite --use_xpu --ir_optim
 ```
 
 ### Client prediction

python/examples/xpu/fit_a_line_xpu/test_server.py

@@ -13,7 +13,7 @@
 # limitations under the License.
 # pylint: disable=doc-string-missing
 
-from paddle_serving_server_gpu.web_service import WebService
+from paddle_serving_server.web_service import WebService
 import numpy as np
 
 

python/examples/xpu/resnet_v2_50_xpu/README.md

@@ -12,7 +12,7 @@ tar -xzvf resnet_v2_50_imagenet.tar.gz
 ### Start Service
 
 ```
-python -m paddle_serving_server_gpu.serve --model resnet_v2_50_imagenet_model --port 9393 --use_lite --use_xpu --ir_optim
+python -m paddle_serving_server.serve --model resnet_v2_50_imagenet_model --port 9393 --use_lite --use_xpu --ir_optim
 ```
 
 ### Client Prediction

python/examples/xpu/resnet_v2_50_xpu/README_CN.md

@@ -12,7 +12,7 @@ tar -xzvf resnet_v2_50_imagenet.tar.gz
 ### 启动服务端
 
 ```
-python -m paddle_serving_server_gpu.serve --model resnet_v2_50_imagenet_model --port 9393 --use_lite --use_xpu --ir_optim
+python -m paddle_serving_server.serve --model resnet_v2_50_imagenet_model --port 9393 --use_lite --use_xpu --ir_optim
 ```
 
 ### 客户端预测

python/examples/yolov4/README.md

@@ -12,7 +12,7 @@ tar -xzvf yolov4.tar.gz
 ## Start RPC Service
 
 ```
-python -m paddle_serving_server_gpu.serve --model yolov4_model --port 9393 --gpu_ids 0
+python -m paddle_serving_server.serve --model yolov4_model --port 9393 --gpu_ids 0
 ```
 
 ## Prediction

python/examples/yolov4/README_CN.md

@@ -12,7 +12,7 @@ tar -xzvf yolov4.tar.gz
 ## 启动RPC服务
 
 ```
-python -m paddle_serving_server_gpu.serve --model yolov4_model --port 9393 --gpu_ids 0
+python -m paddle_serving_server.serve --model yolov4_model --port 9393 --gpu_ids 0
 ```
 
 ## 预测

python/paddle_serving_server/serve.py

@@ -23,7 +23,6 @@ import json
 import base64
 import time
 from multiprocessing import Pool, Process
-from paddle_serving_server import serve_args
 from flask import Flask, request
 import sys
 if sys.version_info.major == 2:
@@ -91,7 +90,58 @@ def serve_args():
         help="container_id for authentication")
     return parser.parse_args()
 
-def start_gpu_card_model(port, args, index = 0, gpuid):  # pylint: disable=doc-string-missing
+def start_standard_model(serving_port):  # pylint: disable=doc-string-missing
+    args = parse_args()
+    thread_num = args.thread
+    model = args.model
+    port = serving_port
+    workdir = args.workdir
+    device = args.device
+    mem_optim = args.mem_optim_off is False
+    ir_optim = args.ir_optim
+    max_body_size = args.max_body_size
+    use_mkl = args.use_mkl
+    use_encryption_model = args.use_encryption_model
+    use_multilang = args.use_multilang
+
+    if model == "":
+        print("You must specify your serving model")
+        exit(-1)
+
+    import paddle_serving_server as serving
+    op_maker = serving.OpMaker()
+    read_op = op_maker.create('general_reader')
+    general_infer_op = op_maker.create('general_infer')
+    general_response_op = op_maker.create('general_response')
+
+    op_seq_maker = serving.OpSeqMaker()
+    op_seq_maker.add_op(read_op)
+    op_seq_maker.add_op(general_infer_op)
+    op_seq_maker.add_op(general_response_op)
+
+    server = None
+    if use_multilang:
+        server = serving.MultiLangServer()
+    else:
+        server = serving.Server()
+    server.set_op_sequence(op_seq_maker.get_op_sequence())
+    server.set_num_threads(thread_num)
+    server.set_memory_optimize(mem_optim)
+    server.set_ir_optimize(ir_optim)
+    server.use_mkl(use_mkl)
+    server.set_max_body_size(max_body_size)
+    server.set_port(port)
+    server.use_encryption_model(use_encryption_model)
+    if args.product_name != None:
+        server.set_product_name(args.product_name)
+    if args.container_id != None:
+        server.set_container_id(args.container_id)
+
+    server.load_model_config(model)
+    server.prepare_server(workdir=workdir, port=port, device=device)
+    server.run_server()
+
+def start_gpu_card_model(index, gpuid, port, args):  # pylint: disable=doc-string-missing
     workdir = args.workdir
     gpuid = int(gpuid)
     device = "gpu"
@@ -113,7 +163,7 @@ def start_gpu_card_model(port, args, index = 0, gpuid):  # pylint: disable=doc-s
         print("You must specify your serving model")
         exit(-1)
 
-    import paddle_serving_server_gpu as serving
+    import paddle_serving_server as serving
     op_maker = serving.OpMaker()
     read_op = op_maker.create('general_reader')
     general_infer_op = op_maker.create('general_infer')

python/pipeline/local_service_handler.py

@@ -15,8 +15,8 @@
 import os
 import logging
 import multiprocessing
-#from paddle_serving_server_gpu import OpMaker, OpSeqMaker
-#from paddle_serving_server_gpu import Server as GpuServer
+#from paddle_serving_server import OpMaker, OpSeqMaker
+#from paddle_serving_server import Server as GpuServer
 #from paddle_serving_server import Server as CpuServer
 from . import util
 #from paddle_serving_app.local_predict import LocalPredictor
@@ -235,7 +235,7 @@ class LocalServiceHandler(object):
             server = Server()
         else:
             #gpu or arm
-            from paddle_serving_server_gpu import OpMaker, OpSeqMaker, Server
+            from paddle_serving_server import OpMaker, OpSeqMaker, Server
             op_maker = OpMaker()
             read_op = op_maker.create('general_reader')
             general_infer_op = op_maker.create('general_infer')

python/setup.py.server_gpu.in

@@ -19,7 +19,7 @@ from __future__ import print_function
 from setuptools import setup, Distribution, Extension
 from setuptools import find_packages
 from setuptools import setup
-from paddle_serving_server_gpu.version import serving_server_version, cuda_version
+from paddle_serving_server.version import serving_server_version, cuda_version
 import util
 
 if cuda_version != "trt":
@@ -27,34 +27,34 @@ if cuda_version != "trt":
 
 max_version, mid_version, min_version = util.python_version()
 # gen pipeline proto code
-util.gen_pipeline_code("paddle_serving_server_gpu")
+util.gen_pipeline_code("paddle_serving_server")
 
 REQUIRED_PACKAGES = [
     'six >= 1.10.0', 'protobuf >= 3.11.0', 'grpcio <= 1.33.2', 'grpcio-tools <= 1.33.2',
     'flask >= 1.1.1', 'func_timeout', 'pyyaml'
 ]
 
-packages=['paddle_serving_server_gpu',
-          'paddle_serving_server_gpu.proto',
-          'paddle_serving_server_gpu.pipeline',
-          'paddle_serving_server_gpu.pipeline.proto',
-          'paddle_serving_server_gpu.pipeline.gateway',
-          'paddle_serving_server_gpu.pipeline.gateway.proto']
+packages=['paddle_serving_server',
+          'paddle_serving_server.proto',
+          'paddle_serving_server.pipeline',
+          'paddle_serving_server.pipeline.proto',
+          'paddle_serving_server.pipeline.gateway',
+          'paddle_serving_server.pipeline.gateway.proto']
 
-package_dir={'paddle_serving_server_gpu':
-             '${PADDLE_SERVING_BINARY_DIR}/python/paddle_serving_server_gpu',
-             'paddle_serving_server_gpu.proto':
-             '${PADDLE_SERVING_BINARY_DIR}/python/paddle_serving_server_gpu/proto',
-             'paddle_serving_server_gpu.pipeline':
-             '${PADDLE_SERVING_BINARY_DIR}/python/paddle_serving_server_gpu/pipeline',
-             'paddle_serving_server_gpu.pipeline.proto':
-             '${PADDLE_SERVING_BINARY_DIR}/python/paddle_serving_server_gpu/pipeline/proto',
-             'paddle_serving_server_gpu.pipeline.gateway':
-             '${PADDLE_SERVING_BINARY_DIR}/python/paddle_serving_server_gpu/pipeline/gateway',
-             'paddle_serving_server_gpu.pipeline.gateway.proto':
-             '${PADDLE_SERVING_BINARY_DIR}/python/paddle_serving_server_gpu/pipeline/gateway/proto'}
+package_dir={'paddle_serving_server':
+             '${PADDLE_SERVING_BINARY_DIR}/python/paddle_serving_server',
+             'paddle_serving_server.proto':
+             '${PADDLE_SERVING_BINARY_DIR}/python/paddle_serving_server/proto',
+             'paddle_serving_server.pipeline':
+             '${PADDLE_SERVING_BINARY_DIR}/python/paddle_serving_server/pipeline',
+             'paddle_serving_server.pipeline.proto':
+             '${PADDLE_SERVING_BINARY_DIR}/python/paddle_serving_server/pipeline/proto',
+             'paddle_serving_server.pipeline.gateway':
+             '${PADDLE_SERVING_BINARY_DIR}/python/paddle_serving_server/pipeline/gateway',
+             'paddle_serving_server.pipeline.gateway.proto':
+             '${PADDLE_SERVING_BINARY_DIR}/python/paddle_serving_server/pipeline/gateway/proto'}
 
-package_data={'paddle_serving_server_gpu': ['pipeline/gateway/libproxy_server.so'],}
+package_data={'paddle_serving_server': ['pipeline/gateway/libproxy_server.so'],}
 
 setup(
     name='paddle-serving-server-gpu',