Set default worker to 1 (kubeflow#1106)

KFServer uses the number of cores on the machine to set the number of process in its tornado service which can delay the initialization time and increase the memory usage a lot.

A local testing suggests that KFServer loaded 64 processes and used more than 500Mb for a simple SKLearn model. Once I set the worker number to 1, the memory usage was reduced to around 100Mb. 
```
[I 200927 18:26:06 kfserver:88] Registering model: mlguild-iris-svm
[I 200927 18:26:06 kfserver:77] Listening on port 8080
[I 200927 18:26:06 kfserver:79] Will fork 0 workers
[I 200927 18:26:06 process:126] Starting 64 processes
```

python/kfserving/kfserving/kfserver.py

@@ -38,7 +38,7 @@
                     help='The GRPC Port listened to by the model server.')
 parser.add_argument('--max_buffer_size', default=DEFAULT_MAX_BUFFER_SIZE, type=int,
                     help='The max buffer size for tornado.')
-parser.add_argument('--workers', default=0, type=int,
+parser.add_argument('--workers', default=1, type=int,
                     help='The number of works to fork')
 args, _ = parser.parse_known_args()