Apply suggestion from @Copilot

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>

vllm_omni/engine/arg_utils.py

@@ -25,7 +25,7 @@ class OmniEngineArgs(EngineArgs):
                 "model_config.engine_output_type for schedulers to use."
             ),
         )
-        parser.add_argument("--model-stage", type=str, default=EngineArgs.model_stage, 
+        parser.add_argument("--model-stage", type=str, default=OmniEngineArgs.model_stage, 
         help="Declare model stage (e.g., 'thinker', 'talker', 'token2wav'). This will be written into model_config.model_stage for schedulers to use.")
         return parser