fix bug

python/paddle_serving_server_gpu/__init__.py

@@ -306,6 +306,9 @@ class Server(object):
         self.check_local_bin()
         if not self.use_local_bin:
             self.download_bin()
+            # wait for other process to download server bin
+            while not os.path.exists(self.server_path):
+                time.sleep(1)
         else:
             print("Use local bin : {}".format(self.bin_path))
         command = "{} " \
@@ -337,8 +340,5 @@ class Server(object):
                       self.gpuid,)
         print("Going to Run Comand")
         print(command)
-        # wait for other process to download server bin
-        while not os.path.exists(self.server_path):
-            time.sleep(1)
 
         os.system(command)

tools/serving_build.sh

@@ -164,6 +164,7 @@ function python_test_fit_a_line() {
             fi
             ;;
         GPU)
+            export CUDA_VISIBLE_DEVICES=0
             # test rpc
             check_cmd "python -m paddle_serving_server_gpu.serve --model uci_housing_model --port 9393 --thread 4 --gpu_ids 0 > /dev/null &"
             sleep 5 # wait for the server to start
@@ -298,6 +299,7 @@ function python_test_bert() {
             echo "bert RPC inference pass" 
             ;;
         GPU)
+            export CUDA_VISIBLE_DEVICES=0
             pip install paddlehub
             # Because download from paddlehub may timeout,
             # download the model from bos(max_seq_len=128).