[BugFix] Qwen3-Omni / Qwen2.5-Omni thinker batching with audio input (vllm-project#451)

Signed-off-by: yinpeiqi <yinpeiqi809@gmail.com>

Author: yinpeiqi

vllm_omni/model_executor/models/qwen2_5_omni/qwen2_5_omni_thinker.py

@@ -90,7 +90,8 @@ def _parse_and_validate_audio_input(self, **kwargs: object) -> Qwen2_5OmniAudioF
         ):
             feature_attention_mask = feature_attention_mask.reshape(-1, feature_attention_mask.shape[-1])
         elif feature_attention_mask is not None and isinstance(feature_attention_mask, list):
-            feature_attention_mask = torch.cat(feature_attention_mask, dim=-1)
+            for i in range(len(feature_attention_mask)):
+                feature_attention_mask[i] = feature_attention_mask[i].reshape(-1)
         return Qwen2_5OmniAudioFeatureInputs(
             type="audio_features",
             input_features=input_audio_features,