[Refactor][OutputProcessor 2/8]: OmniRequestOutput should inherit RequestOutput and no nested wrap-up (#5146)

Signed-off-by: Boao Shi <aoibosh@connect.hku.hk>
Signed-off-by: bowieshi <aoibosh@connect.hku.hk>
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: R2-Y <ruiruyang2@gmail.com>
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
Signed-off-by: Shi Boao Bowie <aoibosh@connect.hku.hk>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: ruirui(rein) yang <73573651+R2-Y@users.noreply.github.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

tests/entrypoints/openai_api/test_serving_speech.py

@@ -180,10 +180,10 @@ def create_mock_audio_output_for_test(
     audio_tensor = torch.sin(torch.linspace(0, 440 * 2 * torch.pi, num_samples))
     mock_request_output = MockRequestOutput(request_id=request_id, audio_tensor=audio_tensor)
 
-    return OmniRequestOutput(
+    return OmniRequestOutput.from_stage_output(
+        mock_request_output,
         stage_id=0,
         final_output_type="audio",
-        request_output=mock_request_output,
     )
 
 
@@ -2292,10 +2292,10 @@ class TestStreamingResponse:
                     self.prompt_logprobs = None
                     self.kv_transfer_params = None
 
-            return OmniRequestOutput(
+            return OmniRequestOutput.from_stage_output(
+                MockRequestOutput(audio_tensor=chunk),
                 stage_id=0,
                 final_output_type="audio",
-                request_output=MockRequestOutput(audio_tensor=chunk),
                 finished=finished,
             )
 
@@ -3441,10 +3441,10 @@ class TestWAVStreaming:
                     self.prompt_logprobs = None
                     self.kv_transfer_params = None
 
-            return OmniRequestOutput(
+            return OmniRequestOutput.from_stage_output(
+                MockRequestOutput(audio_tensor=chunk),
                 stage_id=0,
                 final_output_type="audio",
-                request_output=MockRequestOutput(audio_tensor=chunk),
                 finished=finished,
             )