[Model] Default MOSS Local 1.5 to adaptive CUDA MRV2 with MPS (#8438)

Signed-off-by: Sy03 <1370724210@qq.com>

tests/entrypoints/openai_api/test_serving_speech.py

@@ -61,6 +61,7 @@ from vllm_omni.entrypoints.openai.tts_adapters.base import (
 )
 from vllm_omni.entrypoints.openai.tts_adapters.capabilities import load_supported_speakers
 from vllm_omni.entrypoints.openai.tts_adapters.ming_tts import MingTTSAdapter
+from vllm_omni.entrypoints.openai.tts_adapters.moss_tts import MossTTSAdapter
 from vllm_omni.entrypoints.openai.tts_adapters.qwen3_tts import Qwen3TTSAdapter, Qwen3TTSCodecLimitError
 from vllm_omni.entrypoints.openai.tts_adapters.voxtral import VoxtralTTSAdapter
 from vllm_omni.entrypoints.serve.utils import errors as serve_errors
@@ -84,6 +85,42 @@ pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
 logger = logging.getLogger(__name__)
 
 
+@pytest.mark.parametrize("sse", [False, True])
+@pytest.mark.parametrize("payload", [None, "empty", "valid"])
+@pytest.mark.asyncio
+async def test_moss_empty_stream_is_an_error(mocker, sse, payload):
+    serving = OmniOpenAIServingSpeech.__new__(OmniOpenAIServingSpeech)
+    serving._tts_model_type = "moss_tts"
+    serving.engine_client = SimpleNamespace(
+        model_config=SimpleNamespace(model="OpenMOSS-Team/MOSS-TTS-Local-Transformer-v1.5")
+    )
+    serving._adapter = MossTTSAdapter(SpeechServingContext(server=serving, engine_client=serving.engine_client))
+    ready = mocker.patch.object(serving, "_mark_ref_audio_artifact_ready_for_request")
+    discard = mocker.patch.object(serving, "_discard_ref_audio_artifact_warmup")
+
+    async def results():
+        if payload is not None:
+            audio = torch.zeros(320) if payload == "valid" else torch.empty(0)
+            yield SimpleNamespace(multimodal_output={"model_outputs": audio, "sr": 24000})
+            yield SimpleNamespace(multimodal_output={"model_outputs": torch.empty(0), "sr": 24000})
+
+    if sse:
+        events = [event async for event in serving._generate_audio_sse_events(results(), "moss-empty")]
+        assert any("speech.audio.done" in event for event in events) == (payload == "valid")
+        assert any("speech.audio.error" in event for event in events) == (payload != "valid")
+    else:
+        chunks = serving._generate_audio_chunks(results(), "moss-empty", response_format="wav")
+        if payload == "valid":
+            output = [chunk async for chunk in chunks]
+            assert len(output) == 2 and output[0].startswith(b"RIFF")
+            assert len(output[1]) == 640
+        else:
+            with pytest.raises(TTSGenerationError, match="no audio"):
+                await anext(chunks)
+    assert ready.call_count == int(payload == "valid")
+    assert discard.call_count == int(payload != "valid")
+
+
 class TestAudioMixin:
     @pytest.fixture
     def audio_mixin(self):

tests/entrypoints/openai_api/test_serving_speech_metrics.py

@@ -283,7 +283,7 @@ async def test_streaming_speech_does_not_count_empty_payload_as_first_packet(mon
         request_id="speech-test",
         request_arrival_ts=100.0,
     )
-    assert len([chunk async for chunk in chunks]) == 2
+    assert [chunk async for chunk in chunks] == [b"\0\0" * 320]
     assert metrics.ttfp_calls == [("1", "2", pytest.approx(0.25))]
     assert metrics.underrun_calls == [("1", "2", pytest.approx(0.0))]
     assert metrics.continuity_calls == [("1", "2", 100)]
@@ -319,7 +319,11 @@ async def test_streaming_speech_does_not_finalize_continuity_on_validation_error
     def reject_generation(_tts_params, **_kwargs):
         raise RuntimeError("generation validation failed")
 
-    adapter = SimpleNamespace(validates_generation=True, validate_generation=reject_generation)
+    adapter = SimpleNamespace(
+        validates_generation=True,
+        validate_generation=reject_generation,
+        validate_stream_audio=lambda **_kwargs: None,
+    )
     serving = _serving(metrics, adapter=adapter)
     monkeypatch.setattr("vllm_omni.entrypoints.openai.serving_speech.time.time", lambda: 100.25)