[Quantization][Qwen2.5-Omni] Support thinker-only ModelOpt NVFP4 W4A4 checkpoints (#5073)

Signed-off-by: Caspian443 <scrisis843@gmail.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>

tests/engine/test_arg_utils.py

@@ -12,7 +12,7 @@ from unittest.mock import Mock
 import pytest
 from omegaconf import OmegaConf
 from pydantic import ValidationError
-from transformers import PretrainedConfig
+from transformers import PretrainedConfig, Qwen3OmniMoeConfig
 from vllm.engine.arg_utils import EngineArgs
 
 from vllm_omni.config.model import OmniModelConfig
@@ -244,6 +244,28 @@ def test_stage_specific_text_config_override():
     assert omni_config.get_head_size() == talker_head_dim
 
 
+def test_non_override_ar_stage_inputs_embeds_size_matches_hidden_size():
+    """A stage without an embedding-size override keeps the default input width."""
+    vllm_config = EngineArgs().create_model_config()
+    vllm_config.hf_config = Qwen3OmniMoeConfig(enable_audio_output=True)
+
+    omni_config = OmniModelConfig.from_vllm_model_config(
+        vllm_config,
+        model_stage="talker",
+        hf_config_name="talker_config",
+    )
+
+    assert (
+        getattr(
+            omni_config.hf_config.talker_config,
+            "embedding_size",
+            None,
+        )
+        is None
+    )
+    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")