[Refactor] Remove internal stage_configs_path plumbing (#5741)

Signed-off-by: zwhzzz0821 <2831474076@qq.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

examples/offline_inference/covo_audio/end2end.py

@@ -59,7 +59,7 @@ def main(args):
 
     omni = Omni(
         model=args.model_name,
-        stage_configs_path=args.stage_configs_path,
+        deploy_config=args.deploy_config,
         log_stats=args.log_stats,
         stage_init_timeout=args.stage_init_timeout,
         batch_timeout=args.batch_timeout,
@@ -167,10 +167,10 @@ def parse_args():
         help="Sampling rate for audio loading (default: 16000).",
     )
     parser.add_argument(
-        "--stage-configs-path",
+        "--deploy-config",
         type=str,
         default=None,
-        help="Path to stage configs YAML file.",
+        help="Path to a deploy config YAML file.",
     )
     parser.add_argument(
         "--log-stats",

examples/offline_inference/dynin_omni/end2end.py

@@ -876,7 +876,7 @@ def parse_args(repo_root: Path) -> argparse.Namespace:
     parser.add_argument("--task", type=str, required=True, choices=TASK_CHOICES)
     parser.add_argument("--model", type=str, required=True, help="HF repo id or local model directory.")
     parser.add_argument(
-        "--stage-config-path",
+        "--deploy-config",
         type=str,
         default=str(repo_root / "vllm_omni/deploy/dynin_omni.yaml"),
         help="Path to deploy config yaml.",
@@ -1394,8 +1394,8 @@ def main() -> None:
 
     from vllm_omni.entrypoints.omni import Omni
 
-    stage_config_path = str(Path(args.stage_config_path).expanduser())
-    omni = Omni(model=model_source, stage_configs_path=stage_config_path, dtype=args.dtype)
+    deploy_config_path = str(Path(args.deploy_config).expanduser())
+    omni = Omni(model=model_source, deploy_config=deploy_config_path, dtype=args.dtype)
     sampling_params_list = [
         SamplingParams(max_tokens=int(args.max_tokens_per_stage), temperature=0.0, top_p=1.0, detokenize=False)
         for _ in range(omni.num_stages)

examples/offline_inference/hunyuan_image3/end2end.py

@@ -73,7 +73,6 @@ def parse_args():
     )
     parser.add_argument("--sys-type", type=str, default=None, help="Override system prompt type.")
     parser.add_argument("--deploy-config", type=str, default=None, help="Custom deploy YAML path.")
-    parser.add_argument("--stage-configs-path", type=str, default=None, help="Custom legacy stage config YAML path.")
     parser.add_argument(
         "--stream",
         action="store_true",
@@ -146,13 +145,7 @@ def main():
     else:
         bot_task = args.bot_task
 
-    if args.deploy_config is not None and args.stage_configs_path is not None:
-        raise ValueError("--deploy-config and --stage-configs-path are mutually exclusive.")
-
-    deploy_config = args.deploy_config
-    stage_configs_path = args.stage_configs_path
-    if deploy_config is None and stage_configs_path is None:
-        deploy_config = _MODALITY_DEFAULT_DEPLOY_CONFIG[args.modality]
+    deploy_config = args.deploy_config or _MODALITY_DEFAULT_DEPLOY_CONFIG[args.modality]
 
     omni_kwargs = {
         "model": args.model,
@@ -168,10 +161,7 @@ def main():
 
     if additional_config is not None:
         omni_kwargs["additional_config"] = additional_config
-    if deploy_config is not None:
-        omni_kwargs["deploy_config"] = deploy_config
-    else:
-        omni_kwargs["stage_configs_path"] = stage_configs_path
+    omni_kwargs["deploy_config"] = deploy_config
 
     omni = Omni(**omni_kwargs)
 
@@ -272,10 +262,7 @@ def main():
     print(f"  Modality: {args.modality}")
     print(f"  Prompt task: {task}")
     print(f"  Bot task: {bot_task}")
-    if deploy_config is not None:
-        print(f"  Deploy config: {deploy_config}")
-    else:
-        print(f"  Stage config: {stage_configs_path}")
+    print(f"  Deploy config: {deploy_config}")
     print(f"  Num stages: {omni.num_stages}")
     if args.modality in ("text2img", "img2img"):
         print(f"  Inference steps: {args.steps}")

examples/offline_inference/minicpmo/end2end.py

@@ -452,12 +452,6 @@ def parse_args():
         default=None,
         help="Path to a .txt file with one prompt per line (preferred).",
     )
-    parser.add_argument(
-        "--stage-configs-path",
-        type=str,
-        default=None,
-        help="Path to a stage configs file (deprecated; prefer --deploy-config).",
-    )
     parser.add_argument(
         "--deploy-config",
         type=str,

examples/offline_inference/qwen3_omni/end2end.py

@@ -484,10 +484,10 @@ def parse_args():
         help="Path to a .txt file with one prompt per line (preferred).",
     )
     parser.add_argument(
-        "--stage-configs-path",
+        "--deploy-config",
         type=str,
         default=None,
-        help="Path to a stage configs file.",
+        help="Path to a deploy config YAML.",
     )
     parser.add_argument(
         "--video-path",

examples/offline_inference/step_audio2/end2end.py

@@ -232,15 +232,8 @@ def main(args):
         raise ValueError(f"Unknown query type: {args.query_type}")
 
     # Initialize vLLM-Omni with Step-Audio2
-    # Resolve deploy config path. Keep explicit stage_configs_path for legacy
-    # custom configs, but use bundled deploy configs by default.
-    deploy_config_path = None
-    stage_config_path = None
-    if args.stage_configs_path and args.deploy_config:
-        raise ValueError("--stage-configs-path and --deploy-config are mutually exclusive")
-    if args.stage_configs_path:
-        stage_config_path = args.stage_configs_path
-    elif args.deploy_config:
+    # Resolve an explicit deploy config or use the bundled task default.
+    if args.deploy_config:
         deploy_config_path = args.deploy_config
     else:
         configs_dir = Path(__file__).parent.parent.parent.parent / "vllm_omni/deploy"
@@ -262,10 +255,7 @@ def main(args):
         "ray_address": args.ray_address,
         "trust_remote_code": True,
     }
-    if stage_config_path is not None:
-        omni_kwargs["stage_configs_path"] = stage_config_path
-    else:
-        omni_kwargs["deploy_config"] = deploy_config_path
+    omni_kwargs["deploy_config"] = deploy_config_path
 
     omni_llm = Omni(**omni_kwargs)
 
@@ -418,12 +408,6 @@ def parse_args():
             "  - HuggingFace ID: stepfun-ai/Step-Audio-2-mini"
         ),
     )
-    parser.add_argument(
-        "--stage-configs-path",
-        type=str,
-        default=None,
-        help="Path to a legacy stage config YAML file (default: use bundled deploy config)",
-    )
     parser.add_argument(
         "--deploy-config",
         type=str,

examples/offline_inference/text_to_image/text_to_image.py

@@ -92,12 +92,6 @@ def parse_args() -> argparse.Namespace:
         "meituan-longcat/LongCat-Image, OvisAI/Ovis-Image, "
         "stabilityai/stable-diffusion-3.5-medium, Tongyi-MAI/Z-Image-Turbo and etc.",
     )
-    parser.add_argument(
-        "--stage-configs-path",
-        type=str,
-        default=None,
-        help="[Deprecated] Path to a legacy stage_args-format YAML. Prefer --deploy-config.",
-    )
     parser.add_argument(
         "--deploy-config",
         type=str,
@@ -475,8 +469,6 @@ def main():
         omni_kwargs["tensor_parallel_size"] = args.tensor_parallel_size
     if args.enforce_eager is not None:
         omni_kwargs["enforce_eager"] = args.enforce_eager
-    if args.stage_configs_path:
-        omni_kwargs["stage_configs_path"] = args.stage_configs_path
     if args.deploy_config:
         omni_kwargs["deploy_config"] = args.deploy_config
     if use_nextstep:
@@ -515,8 +507,8 @@ def main():
     print(f"  Image size: {args.width}x{args.height}")
     if args.lora_path:
         print(f"  LoRA: scale={args.lora_scale}")
-    if args.stage_configs_path:
-        print(f"  stage-configs-path: {args.stage_configs_path}")
+    if args.deploy_config:
+        print(f"  deploy-config: {args.deploy_config}")
     print(f"{'=' * 60}\n")
 
     # Build LoRA request when --lora-path is set

examples/offline_inference/text_to_speech/fish_speech/end2end.py

@@ -38,7 +38,7 @@ from vllm_omni.utils.tracking_parser import TrackingArgumentParser
 logger = logging.getLogger(__name__)
 
 DEFAULT_MODEL = "fishaudio/s2-pro"
-DEFAULT_STAGE_CONFIG = os.path.join(
+DEFAULT_DEPLOY_CONFIG = os.path.join(
     os.path.dirname(__file__),
     "..",
     "..",
@@ -152,10 +152,7 @@ def _build_omni_kwargs(args, model_name: str) -> dict:
         log_stats=args.log_stats,
         stage_init_timeout=args.stage_init_timeout,
     )
-    if args.deploy_config:
-        omni_kwargs["deploy_config"] = args.deploy_config
-    else:
-        omni_kwargs["stage_configs_path"] = args.stage_configs_path or DEFAULT_STAGE_CONFIG
+    omni_kwargs["deploy_config"] = args.deploy_config or DEFAULT_DEPLOY_CONFIG
     return omni_kwargs
 
 
@@ -278,12 +275,6 @@ def parse_args():
         default=None,
         help="Deploy config YAML path (under vllm_omni/deploy/).",
     )
-    parser.add_argument(
-        "--stage-configs-path",
-        type=str,
-        default=None,
-        help="Path to stage configs YAML (legacy, prefer --deploy-config).",
-    )
     parser.add_argument(
         "--output-dir",
         default="output_audio",

examples/offline_inference/text_to_speech/glm_tts/end2end.py

@@ -145,7 +145,7 @@ def main(args):
 
     omni = Omni(
         model=args.model,
-        stage_configs_path=deploy_config_path,
+        deploy_config=deploy_config_path,
         log_stats=args.log_stats,
         stage_init_timeout=args.stage_init_timeout,
     )

examples/offline_inference/text_to_speech/qwen3_tts/end2end.py

@@ -490,10 +490,10 @@ def parse_args():
         help="Path to a .txt file with one prompt per line (preferred).",
     )
     parser.add_argument(
-        "--stage-configs-path",
+        "--deploy-config",
         type=str,
         default=None,
-        help="Path to a stage configs file.",
+        help="Path to a deploy config YAML.",
     )
     parser.add_argument(
         "--audio-path",

tests/config/test_config_factory.py

@@ -6,7 +6,7 @@ Unit tests for StageConfigFactory and related classes.
 
 import importlib
 import warnings
-from dataclasses import dataclass, fields
+from dataclasses import dataclass
 from pathlib import Path
 from unittest.mock import patch
 
@@ -34,9 +34,8 @@ from vllm_omni.config.stage_config import (
     load_deploy_config,
     merge_pipeline_deploy,
     pipeline_cfg_resolver,
-    strip_parent_engine_args,
 )
-from vllm_omni.engine.arg_utils import SHARED_FIELDS, EngineArgs, internal_blacklist_keys
+from vllm_omni.engine.arg_utils import SHARED_FIELDS, internal_blacklist_keys
 
 pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
 
@@ -475,7 +474,7 @@ class TestStageConfigFactory:
         cli_overrides = {
             "gpu_memory_utilization": 0.9,
             "model": "some_model",  # Internal
-            "stage_configs_path": "/path",  # Internal
+            "deploy_config": "/path",  # Internal
             "batch_timeout": 10,  # Internal
         }
 
@@ -483,7 +482,7 @@ class TestStageConfigFactory:
 
         assert overrides["gpu_memory_utilization"] == 0.9
         assert "model" not in overrides
-        assert "stage_configs_path" not in overrides
+        assert "deploy_config" not in overrides
         assert "batch_timeout" not in overrides
 
     def test_per_stage_override_excludes_internal_keys(self):
@@ -525,49 +524,6 @@ class TestStageResolutionHelpers:
         assert "model" not in overrides
         assert "parallel_config" not in overrides
 
-    def test_strip_parent_engine_args_reports_only_surprising_parent_overrides(self):
-        parent_fields = {f.name: f for f in fields(EngineArgs)}
-        filtered, overridden = strip_parent_engine_args(
-            {
-                "model": "some/model",
-                "stage_configs_path": "/tmp/stages.yaml",
-                "tensor_parallel_size": 4,
-                "worker_extension_cls": "some.Extension",
-                "custom_pipeline_args": {"pipeline_class": "demo.Pipeline"},
-            },
-            parent_fields=parent_fields,
-            keep_keys={"worker_extension_cls"},
-            strip_keys={"stage_configs_path"},
-            no_warn_keys={"model"},
-        )
-
-        assert filtered == {
-            "worker_extension_cls": "some.Extension",
-            "custom_pipeline_args": {"pipeline_class": "demo.Pipeline"},
-        }
-        assert overridden == ["tensor_parallel_size"]
-
-    def test_strip_parent_engine_args_keeps_allowed_media_access_controls(self):
-        parent_fields = {f.name: f for f in fields(EngineArgs)}
-        filtered, overridden = strip_parent_engine_args(
-            {
-                "model": "some/model",
-                "stage_configs_path": "/tmp/stages.yaml",
-                "allowed_local_media_path": "/data/qwentts",
-                "allowed_media_domains": ["example.com"],
-            },
-            parent_fields=parent_fields,
-            keep_keys={"allowed_local_media_path", "allowed_media_domains"},
-            strip_keys={"stage_configs_path"},
-            no_warn_keys={"model"},
-        )
-
-        assert filtered == {
-            "allowed_local_media_path": "/data/qwentts",
-            "allowed_media_domains": ["example.com"],
-        }
-        assert overridden == []
-
 
 class TestPipelineDiscovery:
     """Tests for the central pipeline registry (``OMNI_PIPELINES``)."""

tests/diffusion/quantization/test_quantization_fp8.py

@@ -199,7 +199,7 @@ def _generate_bagel_image(
     config_path = get_deploy_config_path("ci/bagel.yaml")
     omni_kwargs: dict[str, Any] = {
         "model": "ByteDance-Seed/BAGEL-7B-MoT",
-        "stage_configs_path": config_path,
+        "deploy_config": config_path,
         "stage_init_timeout": 300,
     }
     if diffusion_quantization_config:

tests/distributed/omni_connectors/test_bagel_mooncake_connector.py

@@ -314,7 +314,7 @@ def test_bagel_text2img_mooncake_connector(run_level):
         temp_config_file = _resolve_deploy_config(temp_config_file, run_level)
         with OmniRunner(
             "ByteDance-Seed/BAGEL-7B-MoT",
-            stage_configs_path=temp_config_file,
+            deploy_config=temp_config_file,
             stage_init_timeout=300,
         ) as runner:
             generated_image = _generate_bagel_image(runner.omni)

tests/distributed/omni_connectors/test_bagel_shared_memory_connector.py

@@ -251,7 +251,7 @@ def test_bagel_img2img_shared_memory_connector(run_level):
     config_path = _resolve_deploy_config(BAGEL_CI_DEPLOY, run_level)
     with OmniRunner(
         "ByteDance-Seed/BAGEL-7B-MoT",
-        stage_configs_path=config_path,
+        deploy_config=config_path,
     ) as runner:
         generated_image = _generate_bagel_img2img(runner.omni, input_image)
         if run_level == "advanced_model":
@@ -266,7 +266,7 @@ def test_bagel_text2img_shared_memory_connector(run_level):
     config_path = _resolve_deploy_config(BAGEL_CI_DEPLOY, run_level)
     with OmniRunner(
         "ByteDance-Seed/BAGEL-7B-MoT",
-        stage_configs_path=config_path,
+        deploy_config=config_path,
     ) as runner:
         generated_image = _generate_bagel_text2img(runner.omni)
         if run_level == "advanced_model":

tests/e2e/offline_inference/test_audiox_model_expansion.py

@@ -17,7 +17,7 @@ from vllm_omni.platforms import current_omni_platform
 # Override in CI if needed: AUDIOX_TEST_MODEL=<model-or-local-path>
 models = [os.environ.get("AUDIOX_TEST_MODEL", "zhangj1an/audiox_random")]
 
-# (model, stage_configs_path, extra_omni_kwargs) for ``omni_runner`` indirect parametrize
+# (model, deploy_config_path, extra_omni_kwargs) for ``omni_runner`` indirect parametrize
 _OMNI_RUNNER_PARAMS = [(m, None, {"model_class_name": "AudioXPipeline"}) for m in models]
 
 pytestmark = [

tests/e2e/offline_inference/test_bagel_expansion.py

@@ -43,7 +43,7 @@ MODEL = "ByteDance-Seed/BAGEL-7B-MoT"
 BAGEL_STAGE_CONFIG = get_deploy_config_path("ci/bagel.yaml")
 DEFAULT_PROMPT = "<|im_start|>A cute cat<|im_end|>"
 
-# (model, stage_configs_path) for ``@pytest.mark.parametrize("omni_runner", ..., indirect=True)``
+# (model, deploy_config_path) for ``@pytest.mark.parametrize("omni_runner", ..., indirect=True)``
 _OMNI_RUNNER_PARAM = (MODEL, BAGEL_STAGE_CONFIG)
 
 

tests/e2e/offline_inference/test_cosyvoice3_expansion.py

@@ -126,7 +126,7 @@ def _build_reference_inputs(prompt_audio: tuple[np.ndarray, int]) -> list[dict[s
     ]
 
 
-# (model, stage_configs_path, extra_omni_kwargs) for ``@pytest.mark.parametrize("omni_runner", ..., indirect=True)``
+# (model, deploy_config_path, extra_omni_kwargs) for ``@pytest.mark.parametrize("omni_runner", ..., indirect=True)``
 _cosy_deployment = get_deploy_config_path("cosyvoice3.yaml")
 _cosy_model_path = str(_resolve_model_dir())
 _OMNI_RUNNER_PARAMS = [

tests/e2e/offline_inference/test_ernie_image_expansion.py

@@ -17,7 +17,7 @@ from vllm_omni.inputs.data import OmniDiffusionSamplingParams
 
 MODEL = "baidu/ERNIE-Image"
 
-# (model, stage_configs_path, extra_omni_kwargs) for ``omni_runner`` indirect parametrize
+# (model, deploy_config_path, extra_omni_kwargs) for ``omni_runner`` indirect parametrize
 _OMNI_RUNNER_PARAM = (
     MODEL,
     None,

tests/e2e/offline_inference/test_glm_tts_expansion.py

@@ -96,7 +96,7 @@ def test_offline_voice_clone_zh(async_chunk: bool) -> None:
 
     with OmniRunner(
         MODEL,
-        stage_configs_path=_get_deploy_config(async_chunk=async_chunk),
+        deploy_config=_get_deploy_config(async_chunk=async_chunk),
         stage_init_timeout=600,
         trust_remote_code=True,
     ) as omni_runner:

tests/e2e/offline_inference/test_hunyuanimage3_i2t_expansion.py

@@ -52,7 +52,7 @@ pytestmark = [pytest.mark.full_model, pytest.mark.diffusion]
 def omni() -> Generator[Omni, None, None]:
     with OmniRunner(
         MODEL_NAME,
-        stage_configs_path=str(STAGE_CONFIG_PATH),
+        deploy_config=str(STAGE_CONFIG_PATH),
         trust_remote_code=True,
     ) as runner:
         yield runner.omni

tests/e2e/offline_inference/test_longcat_video_avatar.py

@@ -84,7 +84,6 @@ def longcat_omni_runner() -> Generator[OmniRunner, None, None]:
     with OmniRunner(
         model,
         seed=42,
-        stage_configs_path=None,
         model_class_name="LongCatVideoAvatarPipeline",
         additional_config={
             "model_type": "avatar-v1.5",

tests/e2e/offline_inference/test_mammoth_moda2_expansion.py

@@ -38,7 +38,7 @@ _AR_PATCH_SIZE = 16
 MODEL_PATH = "bytedance-research/MammothModa2-Preview"
 T2I_DEPLOY_CONFIG = get_deploy_config_path("mammoth_moda2.yaml")
 
-_OMNI_RUNNER_PARAM = (MODEL_PATH, None, {"deploy_config": T2I_DEPLOY_CONFIG})
+_OMNI_RUNNER_PARAM = (MODEL_PATH, T2I_DEPLOY_CONFIG)
 
 # Golden pixel reference file.  Set UPDATE_GOLDEN=1 to regenerate.
 _GOLDEN_T2I_PATH = Path(__file__).parent / "fixtures" / "mammoth_moda2_t2i_golden.json"

tests/e2e/offline_inference/test_minicpmo_4_5.py

@@ -17,7 +17,7 @@ models = ["openbmb/MiniCPM-o-4_5"]
 _CI_DEPLOY = get_deploy_config_path("minicpmo_4_5.yaml")
 
 
-test_params = [(model, None, {"deploy_config": _CI_DEPLOY, "trust_remote_code": True}) for model in models]
+test_params = [(model, _CI_DEPLOY, {"trust_remote_code": True}) for model in models]
 
 
 def get_question(prompt_type: str = "text") -> str:

tests/e2e/offline_inference/test_moss_tts_nano_expansion.py

@@ -25,7 +25,7 @@ from vllm_omni import Omni
 MODEL_NAME = "OpenMOSS-Team/MOSS-TTS-Nano"
 STAGE_CONFIG = get_deploy_config_path("moss_tts_nano.yaml")
 
-# (model, stage_configs_path, extra_omni_kwargs) for ``omni_runner`` indirect parametrize
+# (model, deploy_config_path, extra_omni_kwargs) for ``omni_runner`` indirect parametrize
 _OMNI_RUNNER_PARAM = (
     MODEL_NAME,
     STAGE_CONFIG,

tests/e2e/offline_inference/test_omnivoice_expansion.py

@@ -20,13 +20,11 @@ from tests.helpers.stage_config import get_deploy_config_path
 MODEL = "k2-fsa/OmniVoice"
 DEPLOY_CONFIG = get_deploy_config_path("omnivoice.yaml")
 
-# OmniRunner tuple: model, legacy stage config path, extra Omni kwargs.
-# The migrated test passes deploy_config through extra Omni kwargs.
+# OmniRunner tuple: model, deploy config path, extra Omni kwargs.
 _OMNI_RUNNER_PARAM = (
     MODEL,
-    None,
+    DEPLOY_CONFIG,
     {
-        "deploy_config": DEPLOY_CONFIG,
         "trust_remote_code": True,
         "log_stats": True,
     },

tests/e2e/offline_inference/test_sensenova_u1_expansion.py

@@ -131,7 +131,7 @@ def test_sensenova_u1_lora_scale_and_deactivation(tmp_path) -> None:
     """Validate LoRA effect, scale sensitivity, bounded perturbation, and clean deactivation."""
     lora_request = _make_file_lora_request(tmp_path / "sensenova_lora")
 
-    with OmniRunner(MODEL, stage_configs_path=None) as runner:
+    with OmniRunner(MODEL) as runner:
         omni = runner.omni
         baseline = _generate(omni)
         img_1x = _generate(omni, lora_request, lora_scale=1.0)

tests/e2e/offline_inference/test_sensenova_u1_img2img_expansion.py

@@ -164,10 +164,7 @@ def _generate_sensenova_u1_img2img(
 def test_sensenova_u1_img2img(run_level):
     """Test SenseNova-U1 img2img (single-stage diffusion, no deploy YAML)."""
     input_image = _load_input_image()
-    with OmniRunner(
-        "SenseNova/SenseNova-U1-8B-MoT",
-        stage_configs_path=None,
-    ) as runner:
+    with OmniRunner("SenseNova/SenseNova-U1-8B-MoT") as runner:
         generated_image = _generate_sensenova_u1_img2img(runner.omni, input_image)
         if run_level == "full_model" or run_level == "advanced_model":
             _validate_pixels(generated_image)
@@ -182,7 +179,6 @@ def test_sensenova_u1_img2img_cache_dit():
     input_image = _load_input_image()
     with OmniRunner(
         "SenseNova/SenseNova-U1-8B-MoT",
-        stage_configs_path=None,
         cache_backend="cache_dit",
     ) as runner:
         _generate_sensenova_u1_img2img(runner.omni, input_image)

tests/e2e/offline_inference/test_sensenova_u1_text2img_expansion.py

@@ -151,10 +151,7 @@ def _generate_sensenova_u1_image(
 @hardware_test(res={"cuda": "H100"})
 def test_sensenova_u1_text2img(run_level):
     """Test SenseNova-U1 text2img (single-stage diffusion, no deploy YAML)."""
-    with OmniRunner(
-        "SenseNova/SenseNova-U1-8B-MoT",
-        stage_configs_path=None,
-    ) as runner:
+    with OmniRunner("SenseNova/SenseNova-U1-8B-MoT") as runner:
         generated_image = _generate_sensenova_u1_image(runner.omni)
         if run_level == "full_model" or run_level == "advanced_model":
             _validate_pixels(generated_image)
@@ -168,7 +165,6 @@ def test_sensenova_u1_text2img_cache_dit():
     """Test SenseNova-U1 text2img with Cache-DiT enabled."""
     with OmniRunner(
         "SenseNova/SenseNova-U1-8B-MoT",
-        stage_configs_path=None,
         cache_backend="cache_dit",
     ) as runner:
         _generate_sensenova_u1_image(runner.omni)

tests/e2e/offline_inference/test_soulxsinger_expansion.py

@@ -159,7 +159,7 @@ def test_soulxsinger_multistage_from_audio(
 
     with OmniRunner(
         model,
-        stage_configs_path=get_deploy_config_path(deploy_yaml),
+        deploy_config=get_deploy_config_path(deploy_yaml),
         async_chunk=False,
     ) as runner:
         sampling = OmniDiffusionSamplingParams(
@@ -212,7 +212,7 @@ def test_soulxsinger_svs_precomputed(soulx_weights: tuple[Path, Path, Path]) ->
 
     with OmniRunner(
         str(base_dir),
-        stage_configs_path=get_deploy_config_path("soulxsinger_svs.yaml"),
+        deploy_config=get_deploy_config_path("soulxsinger_svs.yaml"),
         async_chunk=False,
     ) as runner:
         sampling = OmniDiffusionSamplingParams(

tests/e2e/offline_inference/test_step_audio2_expansion.py

@@ -19,7 +19,7 @@ from vllm_omni.outputs import OmniRequestOutput
 
 MODEL = "stepfun-ai/Step-Audio-2-mini"
 DEPLOY_CONFIG = get_deploy_config_path("step_audio2_ci.yaml")
-TEST_PARAMS = [(MODEL, None, {"deploy_config": DEPLOY_CONFIG, "trust_remote_code": True})]
+TEST_PARAMS = [(MODEL, DEPLOY_CONFIG, {"trust_remote_code": True})]
 
 pytestmark = [pytest.mark.slow, pytest.mark.tts]
 

tests/e2e/offline_inference/test_voxtral_tts_expansion.py

@@ -102,7 +102,7 @@ def test_voxtral_tts_offline_streaming():
     async def _run():
         async_omni = AsyncOmni(
             model=MODEL,
-            stage_configs_path=STAGE_CONFIG,
+            deploy_config=STAGE_CONFIG,
             stage_init_timeout=300,
             enforce_eager=True,
         )

tests/engine/test_arg_utils.py

@@ -4,7 +4,6 @@ invariant to the specific attributes of vLLM config except in cases where we
 explicitly patch values that differ from vLLM.
 """
 
-import argparse
 import inspect
 import json
 import os
@@ -20,7 +19,6 @@ from vllm.engine.arg_utils import EngineArgs
 
 from vllm_omni.config.model import OmniModelConfig
 from vllm_omni.engine.arg_utils import OmniEngineArgs
-from vllm_omni.engine.async_omni_engine import AsyncOmniEngine
 from vllm_omni.engine.stage_init_utils import build_engine_args_dict
 
 pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
@@ -149,19 +147,6 @@ def test_qwen3_tts_startup_task_type_is_validated():
         )
 
 
-def test_from_cli_args_picks_up_stage_configs_path():
-    """from_cli_args should pick up stage_configs_path from namespace."""
-    ns = argparse.Namespace(
-        model="facebook/opt-125m",
-        stage_configs_path="/some/path.yaml",
-        custom_pipeline_args=None,
-    )
-
-    args = OmniEngineArgs.from_cli_args(ns)
-    assert args.stage_configs_path == "/some/path.yaml"
-    assert args.custom_pipeline_args is None
-
-
 def test_qwen3_tts_code2wav_injects_max_position_embeddings(monkeypatch):
     """Ensure Code2Wav mirrors stage max_model_len into nested HF overrides.
 
@@ -418,130 +403,6 @@ def test_non_override_ar_stage_inputs_embeds_size_matches_hidden_size():
     assert omni_config.get_inputs_embeds_size() == omni_config.hf_text_config.hidden_size
 
 
-def test_stage_configs_path_field():
-    """OmniEngineArgs with stage_configs_path should construct without error."""
-    args = OmniEngineArgs(stage_configs_path="/some/path.yaml")
-    assert args.stage_configs_path == "/some/path.yaml"
-
-
-def test_strip_single_engine_args():
-    """_strip_single_engine_args should remove EngineArgs fields but keep omni fields."""
-    kwargs = {
-        # Parent EngineArgs fields — stripped unless explicitly allowlisted
-        "compilation_config": '{"cudagraph_mode": "FULL_AND_PIECEWISE"}',
-        "tensor_parallel_size": 4,
-        "gpu_memory_utilization": 0.9,
-        "model": "some/model",
-        # Parent field that should be kept (allowlisted)
-        "worker_extension_cls": "some.Extension",
-        # OmniEngineArgs-only / non-engine fields — should pass through
-        "stage_configs_path": "/path/to/yaml",
-        "custom_pipeline_args": {"pipeline_class": "my.Pipeline"},
-        "mode": "text-to-image",
-        "lora_path": "/some/lora",
-    }
-
-    filtered = AsyncOmniEngine._strip_single_engine_args(kwargs)
-
-    # Stripped — parent EngineArgs fields
-    assert "compilation_config" not in filtered
-    assert filtered["tensor_parallel_size"] == 4
-    assert "gpu_memory_utilization" not in filtered
-    assert "model" not in filtered
-
-    # Stripped — orchestrator-level OmniEngineArgs field
-    assert "stage_configs_path" not in filtered
-
-    # Kept
-    assert filtered["worker_extension_cls"] == "some.Extension"
-    assert filtered["custom_pipeline_args"] == {"pipeline_class": "my.Pipeline"}
-    assert filtered["mode"] == "text-to-image"
-    assert filtered["lora_path"] == "/some/lora"
-
-
-def test_strip_single_engine_args_model_does_not_trigger_warning(mocker):
-    """model is always in kwargs (callers set it via from_cli_args/asdict),
-    so it should not cause the override warning by itself or appear in it."""
-    mock_warn = mocker.patch("vllm_omni.engine.async_omni_engine.logger.warning")
-
-    # Typical caller kwargs: model is always present, no other parent
-    # EngineArgs fields are explicitly overridden.
-    AsyncOmniEngine._strip_single_engine_args(
-        {
-            "model": "some/model",
-            "custom_pipeline_args": {"pipeline_class": "my.Pipeline"},
-        }
-    )
-    mock_warn.assert_not_called()
-
-    # When there *are* genuinely surprising overrides alongside model,
-    # the warning should mention them but not model. Keep-listed fields such as
-    # tensor_parallel_size are intentionally passed through and should not warn.
-    AsyncOmniEngine._strip_single_engine_args(
-        {
-            "model": "some/model",
-            "compilation_config": '{"cudagraph_mode": "FULL_AND_PIECEWISE"}',
-            "tensor_parallel_size": 4,
-            "custom_pipeline_args": {"pipeline_class": "my.Pipeline"},
-        }
-    )
-    mock_warn.assert_called_once()
-    warned_args = mock_warn.call_args[0][-1]  # the formatted arg list
-    assert "compilation_config" in warned_args
-    assert "tensor_parallel_size" not in warned_args
-    assert "model" not in warned_args
-
-
-def test_new_format_deploy_yaml_does_not_strip_interleave_cli_overrides(tmp_path):
-    """New-format deploy YAMLs must not strip interleave_mm_strings / media_io_kwargs.
-
-    Pytest historically passed ``--stage-configs-path`` for deploy YAMLs; stripping
-    those CLI flags dropped MiniCPM interleaved AV packing and cut Daily-Omni
-    accuracy from ~78% to ~70%.
-    """
-    from vllm_omni.entrypoints.utils import is_new_format_deploy_config
-
-    yaml_path = tmp_path / "minicpm_deploy.yaml"
-    yaml_path.write_text(
-        """
-pipeline: minicpmo_4_5
-async_chunk: true
-stages:
-  - stage_id: 0
-    devices: "0"
-""".strip(),
-        encoding="utf-8",
-    )
-    path = str(yaml_path)
-    assert is_new_format_deploy_config(path)
-
-    kwargs = {
-        "stage_configs_path": path,
-        "trust_remote_code": True,
-        "interleave_mm_strings": True,
-        "media_io_kwargs": {"video": {"fps": 1, "num_frames": 128}},
-        "gpu_memory_utilization": 0.55,
-    }
-    # Mirror AsyncOmniEngine._resolve_stage_configs strip decision.
-    if kwargs.get("stage_configs_path") is not None and not is_new_format_deploy_config(kwargs["stage_configs_path"]):
-        base = AsyncOmniEngine._strip_single_engine_args(dict(kwargs))
-    else:
-        base = dict(kwargs)
-    assert base.get("interleave_mm_strings") is True
-    assert base.get("media_io_kwargs") == {"video": {"fps": 1, "num_frames": 128}}
-    # Parent EngineArgs fields also remain available for deploy merge.
-    assert base.get("gpu_memory_utilization") == 0.55
-
-    legacy = tmp_path / "legacy.yaml"
-    legacy.write_text("stage_args:\n  - stage_id: 0\n", encoding="utf-8")
-    assert not is_new_format_deploy_config(str(legacy))
-    legacy_kwargs = dict(kwargs, stage_configs_path=str(legacy))
-    stripped = AsyncOmniEngine._strip_single_engine_args(legacy_kwargs)
-    assert "interleave_mm_strings" not in stripped
-    assert "media_io_kwargs" not in stripped
-    assert "gpu_memory_utilization" not in stripped
-
-
 # For https://github.com/vllm-project/vllm-omni/issues/3293
 def test_tensor_parallel_size_none_is_handled():
     """Ensure the tensor parallel size of None isn't forwarded."""

tests/engine/test_async_omni_engine_abort.py

@@ -68,7 +68,7 @@ async def test_abort():
     with ExitStack() as after:
         engine = AsyncOmni(
             model=model,
-            stage_configs_path=stage_config,
+            deploy_config=stage_config,
         )
         after.callback(engine.shutdown)
 

tests/engine/test_single_stage_mode.py

@@ -428,7 +428,7 @@ class TestSingleStageModeDetection:
         assert engine.single_stage_mode is False
         assert engine._single_stage_id_filter is None
 
-    def test_stage_configs_path_loads_duplex_runtime_config(self, mocker: MockerFixture):
+    def test_deploy_config_loads_duplex_runtime_config(self, mocker: MockerFixture):
         duplex_session = DuplexSessionRuntimeConfig(max_sessions=2)
         get_pipeline_config = mocker.patch(
             "vllm_omni.engine.async_omni_engine.StageConfigFactory.get_pipeline_config",
@@ -441,7 +441,7 @@ class TestSingleStageModeDetection:
 
         engine = self._make_engine_no_thread(
             mocker,
-            stage_configs_path="/fake/duplex.yaml",
+            deploy_config="/fake/duplex.yaml",
         )
 
         get_pipeline_config.assert_called_once_with(

tests/entrypoints/test_async_omni.py

@@ -364,7 +364,7 @@ async def test_omni_generate_request_id():
     Text modality only; asserts caller-visible ids are preserved across the
     multi-stage orchestrator path on H100.
     """
-    engine = AsyncOmni(model=OMNI_MODEL, stage_configs_path=OMNI_STAGE_CONFIG)
+    engine = AsyncOmni(model=OMNI_MODEL, deploy_config=OMNI_STAGE_CONFIG)
     try:
         for req_id in _OMNI_REQ_IDS:
             async for output in engine.generate(

tests/entrypoints/test_async_omni_diffusion_config.py

@@ -478,12 +478,11 @@ def test_resolve_stage_configs_injects_additional_config_into_diffusion_stage(mo
     )
 
     engine = AsyncOmniEngine.__new__(AsyncOmniEngine)
-    engine._strip_single_engine_args = lambda kwargs: kwargs
 
     _, stage_configs = engine._resolve_stage_configs(
         "dummy-model",
         {
-            "stage_configs_path": "dummy.yaml",
+            "deploy_config": "dummy.yaml",
             "additional_config": {"torchair_graph_config": {"enabled": True}},
         },
         trust_remote_code=False,
@@ -516,12 +515,11 @@ def test_resolve_stage_configs_injects_quantization_config_into_diffusion_stage(
     )
 
     engine = AsyncOmniEngine.__new__(AsyncOmniEngine)
-    engine._strip_single_engine_args = lambda kwargs: kwargs
 
     _, stage_configs = engine._resolve_stage_configs(
         "dummy-model",
         {
-            "stage_configs_path": "dummy.yaml",
+            "deploy_config": "dummy.yaml",
             "quantization_config": {"method": "bitsandbytes"},
         },
         trust_remote_code=False,

tests/entrypoints/test_serve.py

@@ -193,7 +193,7 @@ def test_run_headless_parses_and_forwards_stage_overrides(mocker: MockerFixture)
     with pytest.raises(ValueError, match="No stage config found for stage_id=0"):
         run_headless(args)
 
-    assert captured["args"][1] is None
+    assert len(captured["args"]) == 2
     assert captured["deploy_config_path"] == "/tmp/deploy.yaml"
     assert captured["stage_overrides"] == {"0": {"devices": "0,1"}, "1": {"devices": "2"}}
     assert captured["strategy_config_path"] == "/tmp/strategy.yaml"

tests/entrypoints/test_utils.py

@@ -381,7 +381,6 @@ class TestLoadAndResolveStageConfigs:
 
         config_path, stage_configs, _ = load_and_resolve_stage_configs(
             model="black-forest-labs/FLUX.2-klein-4B",
-            stage_configs_path=None,
             kwargs=kwargs,
             trust_remote_code=False,
             default_stage_cfg_factory=lambda: AsyncOmniEngine._create_default_diffusion_stage_cfg(kwargs),
@@ -390,9 +389,7 @@ class TestLoadAndResolveStageConfigs:
         assert len(stage_configs) == 1
         assert "dtype" in stage_configs[0]["engine_args"]
 
-    def test_stage_configs_path_promotes_new_deploy_yaml_without_expanding_replicas(
-        self, tmp_path, mocker: MockerFixture
-    ):
+    def test_deploy_config_preserves_cli_overrides_and_replicas(self, tmp_path, mocker: MockerFixture):
         deploy_path = tmp_path / "qwen3_multi.yaml"
         deploy_path.write_text(
             'stages:\n  - stage_id: 0\n    devices: "0"\n  - stage_id: 1\n    devices: "1,2,3"\n    num_replicas: 3\n',
@@ -413,18 +410,23 @@ class TestLoadAndResolveStageConfigs:
             "vllm_omni.entrypoints.utils.load_stage_configs_from_model",
             return_value=(returned_stage_configs, None),
         )
+        cli_overrides = {
+            "interleave_mm_strings": True,
+            "media_io_kwargs": {"video": {"fps": 1, "num_frames": 128}},
+            "gpu_memory_utilization": 0.55,
+        }
 
         config_path, stage_configs, _ = load_and_resolve_stage_configs(
             model="dummy-model",
-            stage_configs_path=str(deploy_path),
-            kwargs={},
+            kwargs=cli_overrides,
             trust_remote_code=True,
+            deploy_config_path=str(deploy_path),
         )
 
         load_stage_configs.assert_called_once_with(
             "dummy-model",
             trust_remote_code=True,
-            base_engine_args={},
+            base_engine_args=cli_overrides,
             deploy_config_path=str(deploy_path),
             stage_overrides=None,
             strategy_config_path=None,

tests/helpers/runtime.py

@@ -2635,7 +2635,7 @@ class OmniRunner:
         # affects the test runner wrapper.
         init_timeout: int = 1800,
         log_stats: bool = False,
-        stage_configs_path: str | None = None,
+        deploy_config: str | None = None,
         **kwargs,
     ) -> None:
         startup_t0 = time.perf_counter()
@@ -2653,7 +2653,7 @@ class OmniRunner:
             stage_init_timeout=stage_init_timeout,
             batch_timeout=batch_timeout,
             init_timeout=init_timeout,
-            stage_configs_path=stage_configs_path,
+            deploy_config=deploy_config,
             **kwargs,
         )
         startup_s = time.perf_counter() - startup_t0
@@ -3179,12 +3179,7 @@ def iter_omni_server(
                 print("OmniServer stopping...")
         else:
             if stage_config_path is not None:
-                from vllm_omni.entrypoints.utils import is_new_format_deploy_config
-
-                if is_new_format_deploy_config(stage_config_path):
-                    server_args += ["--deploy-config", stage_config_path]
-                else:
-                    server_args += ["--stage-configs-path", stage_config_path]
+                server_args += ["--deploy-config", stage_config_path]
 
             with (
                 OmniServer(
@@ -3237,7 +3232,7 @@ def iter_omni_runner(
         model = model_prefix + model
         if run_level == "core_model" and request.node.get_closest_marker("diffusion"):
             model = resolve_tiny_model_path(model)
-        with OmniRunner(model, seed=42, stage_configs_path=stage_config_path, **extra_omni_kwargs) as runner:
+        with OmniRunner(model, seed=42, deploy_config=stage_config_path, **extra_omni_kwargs) as runner:
             print("OmniRunner started successfully")
             yield runner
             print("OmniRunner stopping...")

tools/baselines/omni_hash_baseline.py

@@ -147,7 +147,7 @@ def _run_once(model: str, yaml_path: str, *, async_mode: bool) -> list[dict]:
     # (see tests/e2e/accuracy/qwen3_omni). Confirm the exact knob at bench time.
     omni = Omni(
         model,
-        stage_configs_path=yaml_path,
+        deploy_config=yaml_path,
         stage_init_timeout=1800,
         init_timeout=3600,
         async_chunk=async_mode,

vllm_omni/config/omni_config.py

@@ -53,7 +53,6 @@ _NON_STAGE_ENGINE_CLI_FIELDS = frozenset(
         "model",
         "omni",
         "output_modalities",
-        "stage_configs_path",
         "stage_id",
         "tokenizer",
     }

vllm_omni/config/stage_config.py

@@ -4,7 +4,6 @@
 
 from __future__ import annotations
 
-import dataclasses
 import functools
 import re
 import warnings
@@ -56,7 +55,7 @@ def build_stage_runtime_overrides(
     ``internal_keys`` defaults to the union of
     ``arg_utils.internal_blacklist_keys()`` and ``arg_utils.SHARED_FIELDS``
     so that neither orchestrator-only fields nor shared-pipeline fields
-    (``model`` / ``stage_configs_path`` / ``log_stats`` / ``stage_id``) leak
+    (``model`` / ``log_stats`` / ``stage_id``) leak
     into a stage's per-stage runtime overrides — the orchestrator sets those
     uniformly for every stage, they are not per-stage knobs. Callers can
     pass an explicit set for tests or specialized flows.
@@ -90,46 +89,6 @@ def build_stage_runtime_overrides(
     return result
 
 
-def strip_parent_engine_args(
-    kwargs: dict[str, Any],
-    *,
-    parent_fields: dict[str, dataclasses.Field],
-    keep_keys: set[str] | frozenset[str] = frozenset(),
-    strip_keys: set[str] | frozenset[str] = frozenset(),
-    no_warn_keys: set[str] | frozenset[str] = frozenset(),
-) -> tuple[dict[str, Any], list[str]]:
-    """Strip parent ``EngineArgs`` fields before merging into stage YAML."""
-    overridden: list[str] = []
-    result: dict[str, Any] = {}
-
-    for key, value in kwargs.items():
-        if key in strip_keys:
-            continue
-
-        if key not in parent_fields or key in keep_keys:
-            result[key] = value
-            continue
-
-        field_def = parent_fields[key]
-        if field_def.default is not dataclasses.MISSING:
-            default = field_def.default
-        elif field_def.default_factory is not dataclasses.MISSING:
-            default = field_def.default_factory()
-        else:
-            default = dataclasses.MISSING
-
-        if default is dataclasses.MISSING or value is None:
-            continue
-
-        if dataclasses.is_dataclass(default) and not isinstance(default, type):
-            default = asdict(default)
-
-        if value != default and key not in no_warn_keys:
-            overridden.append(key)
-
-    return result, sorted(overridden)
-
-
 def _apply_diffusion_parallel_runtime_overrides(
     engine_args: dict[str, Any],
     runtime_overrides: dict[str, Any],

vllm_omni/engine/arg_utils.py

@@ -167,9 +167,6 @@ class OmniEngineArgs(EngineArgs):
             Required when single-stage mode is active.
         omni_master_port: TCP port for the OmniMasterServer registration
             socket.  Required when single-stage mode is active.
-        stage_configs_path: Optional path to a JSON/YAML file containing
-            stage configurations for the multi-stage pipeline. If None,
-            stage configs are resolved from the model's default configuration.
         output_modalities: Optional list of output modality names to enable
             (e.g. ["text", "audio"]). If None, all modalities supported by
             the model are used.
@@ -231,7 +228,6 @@ class OmniEngineArgs(EngineArgs):
     omni_dp_size_local: int = 1
     omni_lb_policy: str = "random"
     omni_heartbeat_timeout: float = 30.0
-    stage_configs_path: str | None = None
     output_modalities: list[str] | None = None
     log_stats: bool = False
     custom_pipeline_args: dict[str, Any] | None = None
@@ -490,7 +486,6 @@ class OrchestratorArgs:
     ray_address: str | None = None
 
     # === Config Files ===
-    stage_configs_path: str | None = None
     deploy_config: str | None = None
     stage_overrides: str | None = None  # raw JSON string; parsed downstream
     # Optional composable-parallel strategy.yaml; orchestrator reads it, overlays
@@ -582,7 +577,6 @@ SHARED_FIELDS: frozenset[str] = frozenset(
         "model",  # orch: detect model_type; engine: load weights
         "stage_id",  # orch: route (headless); engine: identity
         "log_stats",  # both want the flag
-        "stage_configs_path",  # orch: load legacy YAML; engine: may reference for validation
         "async_chunk",  # orch: read from CLI, redistribute; engine: per-stage flag
         "tokenizer",  # orch: detect model type; engine: tokenization
     }

vllm_omni/engine/async_omni_engine.py

@@ -9,7 +9,6 @@ from __future__ import annotations
 
 import asyncio
 import concurrent.futures
-import dataclasses
 import json
 import queue
 import threading
@@ -24,7 +23,6 @@ import janus
 import torch
 from omegaconf import OmegaConf
 from vllm import envs as vllm_envs
-from vllm.engine.arg_utils import EngineArgs
 from vllm.inputs import PromptType
 from vllm.logger import init_logger
 from vllm.v1.engine import EngineCoreRequest
@@ -34,7 +32,6 @@ from vllm_omni.config.config_factory import StageConfigFactory, with_trust_remot
 from vllm_omni.config.stage_config import (
     DuplexSessionRuntimeConfig,
     load_deploy_config,
-    strip_parent_engine_args,
 )
 from vllm_omni.diffusion.data import DiffusionParallelConfig, parse_attention_config
 from vllm_omni.diffusion.diffusion_engine import supports_audio_output
@@ -69,7 +66,6 @@ from vllm_omni.engine.stage_runtime import (
 )
 from vllm_omni.entrypoints.pd_utils import PDDisaggregationMixin
 from vllm_omni.entrypoints.utils import (
-    is_new_format_deploy_config,
     load_and_resolve_stage_configs,
     parse_stage_overrides,
 )
@@ -85,39 +81,6 @@ if TYPE_CHECKING:
 
 _STARTUP_POLL_INTERVAL_S = 1.0
 _REQUEST_QUEUE_MAXSIZE = 256
-# ============================================================================
-# Parent-EngineArgs field-routing contracts (consumed by
-# AsyncOmniEngine._strip_parent_engine_args when ``stage_configs_path`` is set).
-# ============================================================================
-
-# Fields that must survive the "equal to default → strip" filter because
-# diffusion stages need them even when equal to vllm's default value
-# (e.g. colocate worker setup relies on worker_extension_cls being forwarded).
-_PARENT_ARGS_KEEP: frozenset[str] = frozenset(
-    {
-        "worker_extension_cls",
-        "allowed_local_media_path",
-        "allowed_media_domains",
-        # Legacy stage-config YAMLs may intentionally leave parallel or
-        # distributed knobs unspecified at the stage level and rely on
-        # top-level CLI values to fill them in during the per-stage merge.
-        # Keep these fields so stages that omit them can inherit CLI values,
-        # while stages with explicit YAML values still win because the legacy
-        # stage-config loader prefers stage-local engine args.
-        "tensor_parallel_size",
-    }
-)
-
-# Omni orchestrator-level fields consumed by ``_resolve_stage_configs`` that
-# must never leak into per-stage EngineArgs (``stage_configs_path`` would
-# trigger the ``create_model_config`` guard).
-_PARENT_ARGS_STRIP: frozenset[str] = frozenset({"stage_configs_path"})
-
-
-# Fields always populated by callers (via ``from_cli_args`` / ``asdict``) so
-# their presence as an override is never a surprise — suppress the
-# "override ignored" warning for these.
-_PARENT_ARGS_NO_WARN: frozenset[str] = frozenset({"model"})
 
 
 class AsyncOmniEngine:
@@ -210,10 +173,8 @@ class AsyncOmniEngine:
                 self._omni_master_port,
             )
 
-        # Stage resolution pops deploy_config, so get pipeline-wide settings
-        # beforehand. The stage CLI exposes the same deploy YAML through
-        # stage_configs_path.
-        deploy_config_path = kwargs.get("deploy_config") or kwargs.get("stage_configs_path")
+        # Stage resolution pops deploy_config, so get pipeline-wide settings beforehand.
+        deploy_config_path = kwargs.get("deploy_config")
         # ``trust_remote_code`` is tri-state (bool | None): ``None`` means "not
         # specified" so stage-config resolution can defer to the deploy yaml's
         # per-stage value (see ``with_trust_remote_code_override``). The
@@ -1116,40 +1077,6 @@ class AsyncOmniEngine:
         default_stage_cfg[0]["engine_args"]["model_stage"] = "diffusion"
         return default_stage_cfg
 
-    @staticmethod
-    def _strip_single_engine_args(kwargs: dict[str, Any]) -> dict[str, Any]:
-        """Remove parent ``EngineArgs`` fields from *kwargs*.
-
-        When ``stage_configs_path`` is set, per-stage engine args are defined
-        in the YAML.  Top-level single-engine fields (``compilation_config``,
-        ``tensor_parallel_size``, …) must not leak into per-stage configs via
-        the ``base_engine_args`` merge in ``load_stage_configs_from_yaml`` —
-        they can cause type errors (e.g. ``compilation_config`` as a JSON
-        string rejected by ``VllmConfig``) or silently override YAML values.
-
-        Logs a warning for any parent field whose value differs from the
-        dataclass default, so users know their explicit overrides are ignored.
-        See the module-level ``_PARENT_ARGS_*`` constants for the routing
-        contracts this method enforces.
-        """
-        parent_fields: dict[str, dataclasses.Field] = {f.name: f for f in dataclasses.fields(EngineArgs)}
-        result, overridden = strip_parent_engine_args(
-            kwargs,
-            parent_fields=parent_fields,
-            keep_keys=_PARENT_ARGS_KEEP,
-            strip_keys=_PARENT_ARGS_STRIP,
-            no_warn_keys=_PARENT_ARGS_NO_WARN,
-        )
-
-        if overridden:
-            logger.warning(
-                "stage_configs_path is set — the following top-level engine "
-                "args are ignored (per-stage YAML takes precedence): %s",
-                ", ".join(sorted(overridden)),
-            )
-
-        return result
-
     def _apply_strategy_lb_policy(self, derived: str | None, kwargs: dict[str, Any]) -> None:
         """Apply a strategy-derived ``omni_lb_policy`` to the engine.
 
@@ -1188,7 +1115,6 @@ class AsyncOmniEngine:
     ) -> tuple[str, list[Any]]:
         """Resolve stage configs and inject defaults shared by orchestrator/headless."""
 
-        stage_configs_path = kwargs.get("stage_configs_path", None)
         deploy_config_path = kwargs.pop("deploy_config", None)
         strategy_config_path = kwargs.pop("strategy_config", None)
         stage_overrides_json = kwargs.pop("stage_overrides", None)
@@ -1196,26 +1122,15 @@ class AsyncOmniEngine:
         if explicit_stage_configs is not None:
             logger.warning(
                 "`stage_configs` is not part of the public API. "
-                "Ignoring it and resolving stages from stage_configs_path/model factory."
+                "Ignoring it and resolving stages from deploy_config/model factory."
             )
 
-        # Legacy ``stage_args`` YAMLs own per-stage EngineArgs completely, so
-        # strip parent CLI fields. New-format deploy YAMLs (also accepted via
-        # ``--stage-configs-path``) merge CLI overrides the same way as
-        # ``--deploy-config`` — do not strip, or flags like
-        # ``interleave_mm_strings`` / ``media_io_kwargs`` are silently dropped.
-        if stage_configs_path is not None and not is_new_format_deploy_config(stage_configs_path):
-            base_kwargs = self._strip_single_engine_args(kwargs)
-        else:
-            base_kwargs = kwargs
-
         # Parse --stage-overrides JSON string if provided
         stage_overrides = parse_stage_overrides(stage_overrides_json)
 
         config_path, stage_configs, strategy_lb_policy = load_and_resolve_stage_configs(
             model,
-            stage_configs_path,
-            base_kwargs,
+            kwargs,
             trust_remote_code=trust_remote_code,
             default_stage_cfg_factory=lambda: self._create_default_diffusion_stage_cfg(kwargs),
             deploy_config_path=deploy_config_path,

vllm_omni/entrypoints/async_omni.py

@@ -123,9 +123,8 @@ class AsyncOmni(EngineClient, OmniBase):
     Args:
         model: Model name or path to load.
         **kwargs: Additional keyword arguments.
-            - stage_configs_path: Optional path to YAML file containing stage
-              configurations. If None, configurations are resolved from model
-              pipeline factory.
+            - deploy_config: Optional path to a deploy YAML. If None,
+              configurations are resolved from the model pipeline factory.
             - log_stats: Whether to enable statistics logging.
             - stage_init_timeout: Timeout for per-stage initialization.
             - init_timeout: Total timeout for orchestrator startup.

vllm_omni/entrypoints/cli/serve.py

@@ -945,8 +945,6 @@ def run_headless(args: TrackingNamespace) -> None:
 
     config_path, stage_configs, _ = load_and_resolve_stage_configs(
         model,
-        # The serve CLI no longer accepts legacy stage_args YAMLs.
-        None,
         args_dict,
         # store_true cannot express an explicit False: absent maps to None
         # ("not specified") so the deploy yaml's per-stage value applies.

vllm_omni/entrypoints/openai/api_server.py

@@ -679,7 +679,7 @@ async def build_async_omni_from_stage_config(
         EngineClient instance (AsyncOmni) ready for use
 
     Note:
-        Stage configurations are loaded from args.stage_configs_path if provided,
+        Stage configurations are loaded from ``args.deploy_config`` when provided,
         otherwise from the model's default configuration.
     """
 
@@ -1156,7 +1156,7 @@ async def omni_init_app_state(
     state.openai_serving_duplex = None
     if state.openai_serving_chat is not None and should_enable_duplex_endpoint(
         state.stage_configs,
-        config_path=getattr(args, "stage_configs_path", None) or getattr(args, "deploy_config", None),
+        config_path=getattr(args, "deploy_config", None),
     ):
         from vllm_omni.experimental.fullduplex.openai.serving import OmniDuplexSessionHandler
 

vllm_omni/entrypoints/utils.py

@@ -6,7 +6,6 @@ from dataclasses import fields, is_dataclass
 from pathlib import Path
 from typing import Any, get_args, get_origin
 
-import yaml
 from vllm.logger import init_logger
 from vllm.sampling_params import RequestOutputKind, SamplingParams
 from vllm.transformers_utils.config import get_config, get_hf_file_to_dict
@@ -30,15 +29,6 @@ PROJECT_ROOT = Path(__file__).parent.parent.parent
 logger = init_logger(__name__)
 
 
-def is_new_format_deploy_config(path: str | None) -> bool:
-    """Return True when *path* is a deploy YAML (``stages:`` without legacy ``stage_args:``)."""
-    if not path or not os.path.exists(path):
-        return False
-    with open(path, encoding="utf-8") as f:
-        peek = yaml.safe_load(f) or {}
-    return isinstance(peek, dict) and "stages" in peek and "stage_args" not in peek
-
-
 _DIFFUSERS_CLASS_TO_CONFIG: dict[str, str] = {
     "GlmImagePipeline": "glm_image",
 }
@@ -606,7 +596,6 @@ def parse_stage_overrides(value: Any) -> dict[str, dict[str, Any]] | None:
 
 def load_and_resolve_stage_configs(
     model: str,
-    stage_configs_path: str | None,
     kwargs: dict | None,
     *,
     trust_remote_code: bool | None,
@@ -615,17 +604,15 @@ def load_and_resolve_stage_configs(
     stage_overrides: dict[str, dict[str, Any]] | None = None,
     strategy_config_path: str | None = None,
 ) -> tuple[str, list, str | None]:
-    """Load stage configurations from model or YAML file with fallback to defaults.
+    """Load stage configurations from a deploy YAML or model defaults.
 
     Args:
         model: Model name or path
-        stage_configs_path: Optional path to legacy YAML (stage_args format)
         kwargs: Engine arguments to merge with stage configs
         trust_remote_code: Whether to trust remote code while resolving the model config.
         default_stage_cfg_factory: Optional callable that takes no args and returns
             default stage config list when no configs are found
-        deploy_config_path: Optional path to deploy YAML (new format).
-            Mutually exclusive with ``stage_configs_path``.
+        deploy_config_path: Optional path to a deploy YAML.
         stage_overrides: Per-stage overrides from ``--stage-overrides`` JSON.
             Keys are stage_id strings, values are dicts of overrides.
         strategy_config_path: Optional path to a composable-parallel
@@ -636,65 +623,21 @@ def load_and_resolve_stage_configs(
         the strategy-derived pipeline-wide load-balancer policy (``None`` when no
         strategy set one), returned for the engine to apply.
     """
-    if stage_configs_path is not None and deploy_config_path is not None:
-        raise ValueError(
-            "--stage-configs-path and --deploy-config are mutually exclusive: "
-            "they use different path resolution rules and loading paths. "
-            "Use --deploy-config for new-format YAMLs (preferred); "
-            "--stage-configs-path is kept only for the legacy `stage_args` format "
-            "and will be removed in a future release."
-        )
-    if stage_configs_path is not None and deploy_config_path is None:
-        if not os.path.exists(stage_configs_path):
-            raise FileNotFoundError(
-                f"--stage-configs-path {stage_configs_path!r} does not exist. "
-                "Legacy `stage_configs/` yamls were replaced by `vllm_omni/deploy/<model>.yaml`; "
-                "use --deploy-config. See docs/configuration/stage_configs.md."
-            )
-        if is_new_format_deploy_config(stage_configs_path):
-            deploy_config_path = stage_configs_path
-            stage_configs_path = None
+    config_path = deploy_config_path if deploy_config_path is not None else resolve_model_config_path(model)
+    stage_configs, omni_lb_policy = load_stage_configs_from_model(
+        model,
+        trust_remote_code=trust_remote_code,
+        base_engine_args=kwargs,
+        deploy_config_path=deploy_config_path,
+        stage_overrides=stage_overrides,
+        strategy_config_path=strategy_config_path,
+    )
+    if not stage_configs:
+        if default_stage_cfg_factory is not None:
+            default_stage_cfg = default_stage_cfg_factory()
+            stage_configs = create_config(_convert_dataclasses_to_dict(default_stage_cfg))
         else:
-            logger.warning(
-                "--stage-configs-path is deprecated; migrate %r and use --deploy-config.",
-                stage_configs_path,
-            )
-
-    omni_lb_policy: str | None = None
-    if deploy_config_path is not None:
-        config_path = deploy_config_path
-        stage_configs, omni_lb_policy = load_stage_configs_from_model(
-            model,
-            trust_remote_code=trust_remote_code,
-            base_engine_args=kwargs,
-            deploy_config_path=deploy_config_path,
-            stage_overrides=stage_overrides,
-            strategy_config_path=strategy_config_path,
-        )
-        if not stage_configs:
-            if default_stage_cfg_factory is not None:
-                default_stage_cfg = default_stage_cfg_factory()
-                stage_configs = create_config(_convert_dataclasses_to_dict(default_stage_cfg))
-            else:
-                stage_configs = []
-    elif stage_configs_path is None:
-        config_path = resolve_model_config_path(model)
-        stage_configs, omni_lb_policy = load_stage_configs_from_model(
-            model,
-            trust_remote_code=trust_remote_code,
-            base_engine_args=kwargs,
-            stage_overrides=stage_overrides,
-            strategy_config_path=strategy_config_path,
-        )
-        if not stage_configs:
-            if default_stage_cfg_factory is not None:
-                default_stage_cfg = default_stage_cfg_factory()
-                stage_configs = create_config(_convert_dataclasses_to_dict(default_stage_cfg))
-            else:
-                stage_configs = []
-    else:
-        config_path = stage_configs_path
-        stage_configs = load_stage_configs_from_yaml(stage_configs_path, base_engine_args=kwargs)
+            stage_configs = []
 
     stage_configs = filter_stages(config_path, stage_configs, kwargs)
     logger.debug(f"stage_configs: {stage_configs}")