提交 3e2a327f 编写于 作者: W wangjiawei04

add use_multilang option in gpu part

上级 c5d98039
......@@ -68,6 +68,10 @@ def serve_args():
type=int,
default=512 * 1024 * 1024,
help="Limit sizes of messages")
parser.add_argument(
"--use_multilang",
action='store_true',
help="Use Multi-language-service")
return parser.parse_args()
......
......@@ -54,17 +54,26 @@ def start_gpu_card_model(index, gpuid, args): # pylint: disable=doc-string-miss
op_seq_maker.add_op(general_infer_op)
op_seq_maker.add_op(general_response_op)
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.set_max_body_size(max_body_size)
server.load_model_config(model)
server.prepare_server(workdir=workdir, port=port, device=device)
if gpuid >= 0:
server.set_gpuid(gpuid)
use_multilang = args.use_multilang
if use_multilang:
server = serving.MultiLangServer()
server.set_op_sequence(op_seq_maker.get_op_sequence())
server.load_model_config(model)
server.prepare_server(workdir=workdir, port=port, device=device)
if gpuid >= 0:
raise ValueError("gpuid can not >= 0 in 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.set_max_body_size(max_body_size)
server.load_model_config(model)
server.prepare_server(workdir=workdir, port=port, device=device)
if gpuid >= 0:
server.set_gpuid(gpuid)
server.run_server()
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册