here is my code ,it worked in parallel, but each inference took a hundredfold longer.

without multi process ,each inference cost 20ms,

with multi process, each inference cost 25s.

```
def load_model():
conf_obj = _get_config_obj("tests/ocr/ocr.yml")
model_manange = OCRModel(conf_obj)
model_manange.load_model()
model_manange.status = MODEL_MANAGE_IDLE
return model_manange
def init_multi_load() -> None:
for i in range(3):
model_manage_list.append(load_model())
def infer(data: dict, model_manage_list) -> dict:
for model_manage in model_manage_list:
if model_manage.status == MODEL_MANAGE_IDLE:
model_manage.status = MODEL_MANAGE_WORKING
ret = model_manage.run_model(data)
model_manage.status = MODEL_MANAGE_IDLE
return ret
raise ValueError("no idle model for service")
if __name__ == '__main__':
torch.multiprocessing.set_start_method('spawn', force=True)
model_manage_list = Manager().list()
init_multi_load()
data = {} # just for show case here
for i in range(3):
mp = Process(target=infer, args=(data, model_manage_list,))
mp.start()
while True:
time.sleep(2)
```