[perf] Minicpm o4.5 optimization (#5228)

Signed-off-by: R2-Y <ruiruyang2@gmail.com>
Co-authored-by: Sy03 <1370724210@qq.com>

tests/distributed/omni_connectors/test_adapter_and_flow.py

@@ -8,6 +8,7 @@ from vllm_omni.distributed.omni_connectors.adapter import try_recv_via_connector
 from vllm_omni.distributed.omni_connectors.connectors.shm_connector import SharedMemoryConnector
 from vllm_omni.distributed.omni_connectors.utils.config import ConnectorSpec, OmniTransferConfig
 from vllm_omni.distributed.omni_connectors.utils.initialization import get_connectors_config_for_stage
+from vllm_omni.engine.stage_init_utils import get_stage_connector_spec
 
 pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
 
@@ -217,6 +218,22 @@ def test_get_connectors_for_stage():
     assert stage_2_config["from_stage_1"]["spec"]["name"] == "C2"
 
 
+def test_outgoing_only_async_stage_uses_sender_connector_spec():
+    config = OmniTransferConfig(
+        connectors={
+            ("1", "2"): ConnectorSpec(
+                name="SharedMemoryConnector",
+                extra={"codec_chunk_frames": 25},
+            )
+        }
+    )
+
+    spec = get_stage_connector_spec(config, stage_id=1, async_chunk=True)
+
+    assert spec["name"] == "SharedMemoryConnector"
+    assert spec["extra"] == {"codec_chunk_frames": 25, "role": "sender"}
+
+
 def test_recv_with_missing_metadata(mocker: MockerFixture):
     """Test recv when queue payload is malformed (missing metadata)."""
     # Connector expects metadata but task doesn't have it

tests/distributed/omni_connectors/test_chunk_transfer_adapter.py

@@ -13,6 +13,7 @@ from vllm.v1.core.sched.scheduler import Scheduler as VLLMScheduler
 from vllm.v1.request import RequestStatus
 
 from vllm_omni.data_entry_keys import CodesStruct, MetaStruct, OmniPayload, OmniPayloadStruct
+from vllm_omni.distributed.omni_connectors.adapter import construct_next_stage_streaming_input_prompt
 from vllm_omni.distributed.omni_connectors.transfer_adapter.base import OmniTransferAdapterBase
 from vllm_omni.distributed.omni_connectors.transfer_adapter.chunk_transfer_adapter import (
     OmniChunkTransferAdapter,
@@ -43,6 +44,33 @@ def _req(req_id: str, status: RequestStatus, external_req_id: str | None = None)
     )
 
 
+def test_streaming_payload_can_replace_placeholder_prompt(mocker: MockerFixture) -> None:
+    request = SimpleNamespace(
+        _all_token_ids=[0, 0, 7, 8],
+        _output_token_ids=[7, 8],
+        prompt_token_ids=[0, 0],
+        num_computed_tokens=4,
+        num_prompt_tokens=2,
+        update_block_hashes=mocker.Mock(),
+    )
+    payload = {
+        "ids": {"prompt": [1, 2, 3]},
+        "meta": {
+            "replace_streaming_prompt": True,
+            "next_stage_prompt_len": 7,
+        },
+    }
+
+    construct_next_stage_streaming_input_prompt(payload, request)
+
+    assert request.prompt_token_ids == [0] * 7
+    assert request._all_token_ids == [0] * 7
+    assert request._output_token_ids == []
+    assert request.num_computed_tokens == 0
+    assert request.num_prompt_tokens == 7
+    request.update_block_hashes.assert_called_once_with()
+
+
 @pytest.fixture
 def build_adapter(monkeypatch, mocker: MockerFixture):
     def _build(
@@ -81,6 +109,10 @@ def build_adapter(monkeypatch, mocker: MockerFixture):
             worker_type=model_mode,
             max_num_seqs=max_num_seqs,
             active_stream_window=active_stream_window,
+            stage_connector_config={
+                "name": "SharedMemoryConnector",
+                "extra": connector_extra or {},
+            },
         )
         scheduler_config = SimpleNamespace(max_num_seqs=max_num_seqs)
         adapter = OmniChunkTransferAdapter(
@@ -381,6 +413,26 @@ def test_load_poll_ar_request_additional_information_concats_tensors(build_adapt
     assert request.additional_information["meta"]["finished"].item() is True
 
 
+def test_sender_only_adapter_does_not_park_or_clear_requests(build_adapter):
+    adapter, _ = build_adapter(stage_id=1, connector_extra={"role": "sender"})
+    request = _req("req-1", RequestStatus.WAITING)
+    request.additional_information = {"tts_token_ids": torch.tensor([1])}
+    waiting_queue = DummyWaitingQueue([request])
+    running_queue = []
+
+    adapter.load_async(request)
+    adapter.process_pending_chunks(
+        waiting_queue,
+        running_queue,
+        scheduler_requests={request.request_id: request},
+    )
+
+    assert waiting_queue == [request]
+    assert request.status == RequestStatus.WAITING
+    assert request.additional_information["tts_token_ids"].item() == 1
+    assert adapter._pending_load_reqs == deque()
+
+
 def test_process_and_restore_queues(build_adapter):
     adapter, _ = build_adapter(stage_id=1, max_num_seqs=8)
     waiting_req = _req("w1", RequestStatus.WAITING)

tests/distributed/omni_connectors/test_omni_connector_configs.py

@@ -2,10 +2,15 @@
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 from pathlib import Path
+from types import SimpleNamespace
 
 import pytest
 
 # Use the new import path for initialization utilities
+from vllm_omni.distributed.omni_connectors.utils.config import (
+    stage_receives_chunks,
+    stage_sends_async_output,
+)
 from vllm_omni.distributed.omni_connectors.utils.initialization import load_omni_transfer_config
 
 pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
@@ -38,6 +43,26 @@ def get_config_files():
 config_files = get_config_files()
 
 
+@pytest.mark.parametrize(
+    ("role", "stage_id", "receives", "sends"),
+    [
+        ("sender", 0, False, True),
+        ("receiver", 1, True, False),
+        (None, 0, True, False),
+        (None, None, True, True),
+    ],
+)
+def test_stage_chunk_direction_helpers(role, stage_id, receives, sends):
+    extra = {} if role is None else {"role": role}
+    model_config = SimpleNamespace(
+        stage_id=stage_id,
+        stage_connector_config={"extra": extra},
+    )
+
+    assert stage_receives_chunks(model_config) is receives
+    assert stage_sends_async_output(model_config) is sends
+
+
 @pytest.mark.skipif(len(config_files) == 0, reason="No config files found or directory missing")
 @pytest.mark.parametrize("yaml_file", config_files, ids=lambda p: p.name)
 def test_load_qwen_yaml_configs(yaml_file):