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

Signed-off-by: Sy03 <1370724210@qq.com>
This commit is contained in:
Sy03 authored and GitHub committed 2026-10-06 08:20:46 -07:00
1 parent ee9ab9ea88
commit 7be49aa0ce
30 files changed
+808 -152

No files matched your search

@@ -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)