Merge pull request #388 from MRXLT/0.2.0-cherry-v2

[cherry pick to 0.2.0] doc fix && add mem_optim

README.md

@@ -254,7 +254,7 @@ curl -H "Content-Type:application/json" -X POST -d '{"url": "https://paddle-serv
 - [GPU Benchmarks(Chinese)](doc/GPU_BENCHMARKING.md)
 
 ### FAQ
-- [FAQ(Chinese)](doc/FAQ.md)
+- [FAQ(Chinese)](doc/deprecated/FAQ.md)
 
 
 ### Design

python/paddle_serving_server/serve.py

@@ -38,6 +38,8 @@ def parse_args():  # pylint: disable=doc-string-missing
         help="Working dir of current service")
     parser.add_argument(
         "--device", type=str, default="cpu", help="Type of device")
+    parser.add_argument(
+        "--mem_optim", type=bool, default=False, help="Memory optimize")
     return parser.parse_args()
 
 
@@ -48,6 +50,7 @@ def start_standard_model():  # pylint: disable=doc-string-missing
     port = args.port
     workdir = args.workdir
     device = args.device
+    mem_optim = args.mem_optim
 
     if model == "":
         print("You must specify your serving model")
@@ -67,6 +70,7 @@ def start_standard_model():  # pylint: disable=doc-string-missing
     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.load_model_config(model)
     server.prepare_server(workdir=workdir, port=port, device=device)

python/paddle_serving_server_gpu/__init__.py

@@ -43,6 +43,8 @@ def serve_args():
     parser.add_argument("--gpu_ids", type=str, default="", help="gpu ids")
     parser.add_argument(
         "--name", type=str, default="None", help="Default service name")
+    parser.add_argument(
+        "--mem_optim", type=bool, default=False, help="Memory optimize")
     return parser.parse_args()
 
 

python/paddle_serving_server_gpu/serve.py

@@ -33,6 +33,7 @@ def start_gpu_card_model(index, gpuid, args):  # pylint: disable=doc-string-miss
         port = args.port + index
     thread_num = args.thread
     model = args.model
+    mem_optim = args.mem_optim
     workdir = "{}_{}".format(args.workdir, gpuid)
 
     if model == "":
@@ -53,6 +54,7 @@ def start_gpu_card_model(index, gpuid, args):  # pylint: disable=doc-string-miss
     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.load_model_config(model)
     server.prepare_server(workdir=workdir, port=port, device=device)