fix missing arg_parser

api_server.py

@@ -29,6 +29,7 @@ from vllm.entrypoints.openai.serving_completion import OpenAIServingCompletion
 from vllm.entrypoints.openai.serving_embedding import OpenAIServingEmbedding
 from vllm.logger import init_logger
 from vllm.usage.usage_lib import UsageContext
+from vllm.utils import FlexibleArgumentParser
 
 TIMEOUT_KEEP_ALIVE = 5  # seconds
 
@@ -61,7 +62,9 @@ app = fastapi.FastAPI(lifespan=lifespan)
 
 
 def parse_args():
-    parser = make_arg_parser()
+    parser_text = FlexibleArgumentParser(
+        description="vLLM OpenAI-Compatible RESTful API server.")
+    parser = make_arg_parser(parser_text)
     return parser.parse_args()