[Config Refactor] sentinel default precedence (#3078)

Signed-off-by: lishunyang <lishunyang12@163.com>
Signed-off-by: xiaohajiayou <923390377@qq.com>
Co-authored-by: lishunyang <lishunyang12@163.com>

examples/offline_inference/bagel/end2end.py

@@ -116,6 +116,9 @@ def parse_args():
         help="Temperature for text generation sampling (default: 0.3).",
     )
 
+    from vllm_omni.engine.arg_utils import nullify_stage_engine_defaults
+
+    nullify_stage_engine_defaults(parser)
     args = parser.parse_args()
     return args
 

examples/offline_inference/cosyvoice3/verify_e2e_cosyvoice.py

@@ -57,7 +57,6 @@ def run_e2e():
     omni = Omni(
         model=args.model,
         deploy_config=args.deploy_config,
-        trust_remote_code=True,
         tokenizer=args.tokenizer,
         log_stats=True,
     )

examples/offline_inference/custom_pipeline/image_to_image/image_edit.py

@@ -118,6 +118,9 @@ def parse_args() -> argparse.Namespace:
         help='JSON profiler config for torch/cuda profiling, e.g. \'{"profiler":"torch","torch_profiler_dir":"./perf"}\'.',
     )
 
+    from vllm_omni.engine.arg_utils import nullify_stage_engine_defaults
+
+    nullify_stage_engine_defaults(parser)
     return parser.parse_args()
 
 

examples/offline_inference/dynin_omni/end2end.py

@@ -970,6 +970,9 @@ def parse_args(repo_root: Path) -> argparse.Namespace:
     parser.add_argument("--vq-model-audio-local-files-only", action=argparse.BooleanOptionalAction, default=None)
 
     parser.add_argument("--disable-hf-xet", action=argparse.BooleanOptionalAction, default=True)
+    from vllm_omni.engine.arg_utils import nullify_stage_engine_defaults
+
+    nullify_stage_engine_defaults(parser)
     return parser.parse_args()
 
 

examples/offline_inference/helios/end2end.py

@@ -196,6 +196,9 @@ def parse_args() -> argparse.Namespace:
     parser.add_argument("--cfg-parallel-size", type=int, default=1, choices=[1, 2], help="CFG parallel size.")
     parser.add_argument("--tensor-parallel-size", type=int, default=1, help="Tensor parallelism size.")
 
+    from vllm_omni.engine.arg_utils import nullify_stage_engine_defaults
+
+    nullify_stage_engine_defaults(parser)
     return parser.parse_args()
 
 

examples/offline_inference/hunyuan_image3/end2end.py

@@ -135,6 +135,9 @@ def parse_args():
     parser.add_argument("--init-timeout", type=int, default=300, help="Initialization timeout in seconds.")
     parser.add_argument("--enforce-eager", action="store_true", help="Disable torch.compile.")
 
+    from vllm_omni.engine.arg_utils import nullify_stage_engine_defaults
+
+    nullify_stage_engine_defaults(parser)
     return parser.parse_args()
 
 

examples/offline_inference/image_to_image/image_edit.py

@@ -378,6 +378,9 @@ def parse_args() -> argparse.Namespace:
         default=None,
         help='JSON profiler config for torch/cuda profiling, e.g. \'{"profiler":"torch","torch_profiler_dir":"./perf"}\'.',
     )
+    from vllm_omni.engine.arg_utils import nullify_stage_engine_defaults
+
+    nullify_stage_engine_defaults(parser)
     return parser.parse_args()
 
 

examples/offline_inference/image_to_video/image_to_video.py

@@ -211,6 +211,9 @@ def parse_args() -> argparse.Namespace:
         default=None,
         help='JSON profiler config for torch/cuda profiling, e.g. \'{"profiler":"torch","torch_profiler_dir":"./perf"}\'.',
     )
+    from vllm_omni.engine.arg_utils import nullify_stage_engine_defaults
+
+    nullify_stage_engine_defaults(parser)
     return parser.parse_args()
 
 

examples/offline_inference/magi_human/end2end.py

@@ -24,6 +24,9 @@ def parse_args():
     parser.add_argument("--width", type=int, default=448, help="Video width.")
     parser.add_argument("--num-inference-steps", type=int, default=8, help="Number of denoising steps.")
     parser.add_argument("--seed", type=int, default=52, help="Random seed for generation.")
+    from vllm_omni.engine.arg_utils import nullify_stage_engine_defaults
+
+    nullify_stage_engine_defaults(parser)
     return parser.parse_args()
 
 

examples/offline_inference/mammothmodal2_preview/run_mammothmoda2_image_summarize.py

@@ -19,6 +19,7 @@ from vllm import SamplingParams
 from vllm.multimodal.image import convert_image_mode
 
 from vllm_omni import Omni
+from vllm_omni.engine.arg_utils import nullify_stage_engine_defaults
 
 DEFAULT_SYSTEM = "You are a helpful assistant."
 DEFAULT_QUESTION = "Please summarize the content of this image."
@@ -48,6 +49,7 @@ def parse_args() -> argparse.Namespace:
         action="store_true",
         help="Enable diffusion pipeline profiler to display stage durations.",
     )
+    nullify_stage_engine_defaults(parser)
     return parser.parse_args()
 
 

examples/offline_inference/mammothmodal2_preview/run_mammothmoda2_t2i.py

@@ -29,6 +29,7 @@ from PIL import Image
 from vllm.sampling_params import SamplingParams
 
 from vllm_omni import Omni
+from vllm_omni.engine.arg_utils import nullify_stage_engine_defaults
 
 logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
 logger = logging.getLogger(__name__)
@@ -117,6 +118,7 @@ def parse_args() -> argparse.Namespace:
     )
     p.add_argument("--out", type=str, default="output.png", help="Path to save the generated image.")
     p.add_argument("--trust-remote-code", action="store_true", help="Trust remote code when loading the model.")
+    nullify_stage_engine_defaults(p)
     args = p.parse_args()
     if not args.prompt:
         args.prompt = ["A stylish woman with sunglasses riding a motorcycle in NYC."]

examples/offline_inference/ming_flash_omni_tts/end2end.py

@@ -97,7 +97,6 @@ def main():
     omni = Omni(
         model=args.model,
         stage_configs_path=args.stage_configs_path,
-        trust_remote_code=True,
         log_stats=args.log_stats,
         init_timeout=args.init_timeout,
         stage_init_timeout=args.stage_init_timeout,

examples/offline_inference/omnivoice/end2end.py

@@ -89,7 +89,6 @@ def run_e2e():
     omni = Omni(
         model=args.model,
         stage_configs_path=args.stage_config,
-        trust_remote_code=True,
         log_stats=True,
     )
 

examples/offline_inference/qwen3_omni/end2end.py

@@ -21,6 +21,7 @@ from vllm.multimodal.image import convert_image_mode
 from vllm.multimodal.media.audio import load_audio
 from vllm.utils.argparse_utils import FlexibleArgumentParser
 
+from vllm_omni.engine.arg_utils import nullify_stage_engine_defaults
 from vllm_omni.entrypoints.omni import Omni
 
 SEED = 42
@@ -550,6 +551,7 @@ def parse_args():
         help="Model dtype (auto, half, float16, bfloat16, float, float32).",
     )
 
+    nullify_stage_engine_defaults(parser)
     return parser.parse_args()
 
 

examples/offline_inference/text_to_image/text_to_image.py

@@ -300,6 +300,9 @@ def parse_args() -> argparse.Namespace:
         default=None,
         help=("Custom system prompt. Used when --use-system-prompt is custom. "),
     )
+    from vllm_omni.engine.arg_utils import nullify_stage_engine_defaults
+
+    nullify_stage_engine_defaults(parser)
     return parser.parse_args()
 
 

examples/offline_inference/text_to_video/text_to_video.py

@@ -226,6 +226,9 @@ def parse_args() -> argparse.Namespace:
         default=1,
         help="Number of HSDP replica groups.",
     )
+    from vllm_omni.engine.arg_utils import nullify_stage_engine_defaults
+
+    nullify_stage_engine_defaults(parser)
     return parser.parse_args()
 
 

examples/offline_inference/vace/vace_video_generation.py

@@ -71,6 +71,9 @@ def parse_args() -> argparse.Namespace:
     parser.add_argument("--ulysses-degree", type=int, default=1, help="Ulysses SP degree.")
     parser.add_argument("--ring-degree", type=int, default=1, help="Ring attention degree.")
     parser.add_argument("--cfg-parallel-size", type=int, default=1, choices=[1, 2], help="CFG parallel size.")
+    from vllm_omni.engine.arg_utils import nullify_stage_engine_defaults
+
+    nullify_stage_engine_defaults(parser)
     return parser.parse_args()