[Config Refactor][2/N] Pipeline + Deploy Config Schema (#2383)

Signed-off-by: lishunyang <lishunyang12@163.com>
Signed-off-by: reidliu41 <reid201711@gmail.com>
Signed-off-by: Alex Brooks <albrooks@redhat.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: xiaohajiayou <75477391+xiaohajiayou@users.noreply.github.com>
Co-authored-by: Alex Brooks <albrooks@redhat.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

tests/engine/test_arg_utils.py

@@ -39,21 +39,28 @@ def test_default_stage_id_is_concrete_int():
     assert cfg.stage_id == 0
 
 
-def test_multimodal_kwarg_overrides():
+def test_multimodal_kwarg_overrides(mocker):
     """Ensure that overrides in the multimodal config are preserved."""
-    # Get a different value than the default for a multimodal field
     sig = inspect.signature(OmniEngineArgs)
     default_mm_cache = sig.parameters["mm_processor_cache_gb"].default
     override_val = default_mm_cache + 1
 
-    # NOTE: This needs to be a model that resolves to supports_multimodal=True
-    # in vLLM, otherwise we won't have an MM config
+    fake_model_config = SimpleNamespace(
+        multimodal_config=SimpleNamespace(mm_processor_cache_gb=override_val),
+    )
+
+    def _fake_parent_create_model_config(self):
+        assert self.mm_processor_cache_gb == override_val
+        return fake_model_config
+
+    mocker.patch.object(EngineArgs, "create_model_config", _fake_parent_create_model_config)
+    mocker.patch.object(OmniModelConfig, "from_vllm_model_config", side_effect=lambda model_config, **_: model_config)
+
     cfg = OmniEngineArgs(
         model="Qwen/Qwen2-VL-2B-Instruct",
         mm_processor_cache_gb=override_val,
     ).create_model_config()
 
-    # Ensure that the override was applied correctly
     assert cfg.multimodal_config is not None
     assert cfg.multimodal_config.mm_processor_cache_gb == override_val
 

tests/engine/test_async_omni_engine_abort.py

@@ -2,20 +2,24 @@ import asyncio
 import os
 import sys
 from contextlib import ExitStack
-from pathlib import Path
 
 import pytest
 from vllm import SamplingParams
 from vllm.inputs import PromptType
 
-from tests.utils import hardware_test
+# Side-effect import: registers QWEN2_5_OMNI_THINKER_ONLY_PIPELINE in the
+# pipeline registry so the materialized deploy overlay below can select it
+# via its top-level ``pipeline:`` field.
+import vllm_omni.model_executor.models.qwen2_5_omni.pipeline  # noqa: F401, E402
+from tests.utils import get_deploy_config_path, hardware_test
 from vllm_omni.entrypoints.async_omni import AsyncOmni
 
 os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
 
 SEED = 42
 
-stage_config = str(Path(__file__).parent.parent / "e2e" / "stage_configs" / "qwen2_5_omni_thinker_ci.yaml")
+# Single-stage thinker-only deploy, materialized from tests.utils._CI_OVERLAYS.
+stage_config = get_deploy_config_path("ci/qwen2_5_omni_thinker_only.yaml")
 model = "Qwen/Qwen2.5-Omni-7B"