[Entrypoint][Refactor] vLLM-Omni Entrypoint Refactoring (#1908)

Signed-off-by: yinpe <11810305@mail.sustech.edu.cn>
Signed-off-by: Peiqi Yin <yinpeiqi809@gmail.com>
Signed-off-by: yinpeiqi <yinpeiqi809@gmail.com>
Signed-off-by: wuhang <whlbx@hotmail.com>
Signed-off-by: linyueqian <linyueqian@outlook.com>
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: lishunyang <lishunyang12@163.com>
Signed-off-by: Chenguang ZHENG <645327136@qq.com>
Signed-off-by: Peiqi Yin <60515999+yinpeiqi@users.noreply.github.com>
Co-authored-by: yinpe <11810305@mail.sustech.edu.cn>
Co-authored-by: Peiqi Yin <yinpeiqi809@gmail.com>
Co-authored-by: wuhang <whlbx@hotmail.com>
Co-authored-by: Peiqi Yin <60515999+yinpeiqi@users.noreply.github.com>
Co-authored-by: linyueqian <linyueqian@outlook.com>
Co-authored-by: princepride <wangzhipeng628@gmail.com>
Co-authored-by: lishunyang <lishunyang12@163.com>

tests/engine/test_async_omni_engine_input.py

@@ -0,0 +1,63 @@
+from unittest.mock import Mock
+
+import pytest
+from vllm.sampling_params import SamplingParams
+from vllm.v1.engine import EngineCoreRequest
+
+from vllm_omni.engine import OmniEngineCoreRequest
+from vllm_omni.engine.async_omni_engine import AsyncOmniEngine
+
+pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
+
+
+def _make_engine_core_request() -> EngineCoreRequest:
+    return EngineCoreRequest(
+        request_id="req-1",
+        prompt_token_ids=[1, 1, 1],
+        mm_features=None,
+        sampling_params=SamplingParams(max_tokens=8),
+        pooling_params=None,
+        arrival_time=0.0,
+        lora_request=None,
+        cache_salt=None,
+        data_parallel_rank=None,
+    )
+
+
+def test_build_add_request_message_preserves_additional_information():
+    engine = object.__new__(AsyncOmniEngine)
+    params = SamplingParams(max_tokens=8)
+    engine.default_sampling_params_list = [params]
+    engine.stage_metadata = [{"stage_type": "llm"}]
+    engine.supported_tasks = ("speech",)
+
+    input_processor = Mock()
+    input_processor.process_inputs.return_value = _make_engine_core_request()
+    engine.input_processor = input_processor
+
+    output_processor = Mock()
+    engine.output_processors = [output_processor]
+
+    prompt = {
+        "prompt_token_ids": [1, 1, 1],
+        "additional_information": {
+            "text": ["hello world"],
+            "speaker": ["vivian"],
+        },
+    }
+
+    msg = engine._build_add_request_message(
+        request_id="req-1",
+        prompt=prompt,
+        sampling_params_list=[params],
+        final_stage_id=0,
+        arrival_time=0.0,
+    )
+
+    request = msg["prompt"]
+    assert isinstance(request, OmniEngineCoreRequest)
+    assert request.external_req_id == "req-1"
+    assert request.additional_information is not None
+    assert request.additional_information.entries["text"].list_data == ["hello world"]
+    assert request.additional_information.entries["speaker"].list_data == ["vivian"]
+    output_processor.add_request.assert_called_once()