[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>

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,