Keep baseline ASR evaluation unchanged and retain documentation WAVs

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

.buildkite/cuda/test-nightly.yml

@@ -48,6 +48,8 @@ steps:
       - label: ":full_moon: Omni · Doc Test with H100 · 2-GPU"
         source_file_dependencies: omni_qwen3_omni_doc
         timeout_in_minutes: 90
+        artifact_paths:
+          - audio_*.wav
         commands:
           - pytest -s -v tests/examples/ -m "full_model and omni and H100 and B200 and cards_2" --run-level "full_model"
 

tests/model_executor/stage_input_processors/test_qwen3_omni_streaming_helpers.py

@@ -981,27 +981,6 @@ def test_cosyvoice3_full_payload_replace_keys_present() -> None:
     )
 
 
-def test_cosyvoice3_conditioning_replaces_snapshot_while_audio_accumulates() -> None:
-    from vllm_omni.model_executor.stage_input_processors.cosyvoice3 import _FULL_PAYLOAD_REPLACE_KEYS
-    from vllm_omni.outputs.mm_outputs import MultimodalPayload
-    from vllm_omni.outputs.output_modality import OutputModality
-
-    previous = {key: torch.ones(1, 174) for key in _FULL_PAYLOAD_REPLACE_KEYS}
-    padded = {key: torch.zeros(1, 1500) for key in _FULL_PAYLOAD_REPLACE_KEYS}
-    previous["embed.speech_token_len"] = torch.tensor([174])
-    padded["embed.speech_token_len"] = torch.tensor([174])
-    payload = MultimodalPayload.from_dict({**previous, "audio": torch.ones(2)})
-    incoming = MultimodalPayload.from_dict({**padded, "audio": torch.ones(3)})
-    assert payload is not None and incoming is not None
-
-    payload = payload.merged_with(incoming)
-    payload.consolidate_tensors(OutputModality.AUDIO)
-
-    for key in _FULL_PAYLOAD_REPLACE_KEYS:
-        assert torch.equal(payload[key], padded[key])
-    assert torch.equal(payload["audio"], torch.ones(5))
-
-
 def test_ming_flash_omni_thinker2talker_token_only_smoke() -> None:
     """Smoke: ming_flash_omni token-only carries voice metadata."""
     from vllm_omni.model_executor.stage_input_processors.ming_flash_omni import (