Dev/rebase v0.15.0 (#1159)

Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>

examples/offline_inference/qwen2_5_omni/end2end.py

@@ -410,7 +410,7 @@ def main(args):
         elif stage_outputs.final_output_type == "audio":
             for output in stage_outputs.request_output:
                 request_id = output.request_id
-                audio_tensor = output.multimodal_output["audio"]
+                audio_tensor = output.outputs[0].multimodal_output["audio"]
                 output_wav = os.path.join(output_dir, f"output_{request_id}.wav")
                 sf.write(output_wav, audio_tensor.detach().cpu().numpy(), samplerate=24000)
                 print(f"Request ID: {request_id}, Saved audio to {output_wav}")

examples/offline_inference/qwen3_omni/end2end.py

@@ -418,7 +418,7 @@ def main(args):
         elif stage_outputs.final_output_type == "audio":
             for output in stage_outputs.request_output:
                 request_id = output.request_id
-                audio_tensor = output.multimodal_output["audio"]
+                audio_tensor = output.outputs[0].multimodal_output["audio"]
                 output_wav = os.path.join(output_dir, f"output_{request_id}.wav")
 
                 # Convert to numpy array and ensure correct format

examples/offline_inference/qwen3_tts/end2end.py

@@ -244,9 +244,9 @@ def main(args):
     for stage_outputs in omni_generator:
         for output in stage_outputs.request_output:
             request_id = output.request_id
-            audio_tensor = output.multimodal_output["audio"]
+            audio_tensor = output.outputs[0].multimodal_output["audio"]
             output_wav = os.path.join(output_dir, f"output_{request_id}.wav")
-            audio_samplerate = output.multimodal_output["sr"].item()
+            audio_samplerate = output.outputs[0].multimodal_output["sr"].item()
             # Convert to numpy array and ensure correct format
             audio_numpy = audio_tensor.float().detach().cpu().numpy()
 

examples/online_serving/qwen3_tts/openai_speech_client.py

@@ -111,6 +111,10 @@ def run_tts_generation(args) -> None:
         print(response.text)
         return
 
+    if response.content.decode("utf-8").startswith('{"error"'):
+        print(f"Error: {response.content.decode('utf-8')}")
+        return
+
     # Save audio response
     output_path = args.output or "tts_output.wav"
     with open(output_path, "wb") as f: