[Test] Fit Qwen2.5 online serving placement to its two-card allocation

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

tests/e2e/online_serving/test_qwen2_5_omni_expansion.py

@@ -21,7 +21,13 @@ models = ["Qwen/Qwen2.5-Omni-7B"]
 
 # Single CI deploy YAML; rocm/xpu deltas are picked automatically via the
 # platforms: section in vllm_omni/deploy/ci/qwen2_5_omni.yaml.
-stage_configs = [modify_stage_config(get_deploy_config_path("ci/qwen2_5_omni.yaml"))]
+stage_configs = [
+    modify_stage_config(
+        get_deploy_config_path("ci/qwen2_5_omni.yaml"),
+        # This suite requests two cards; Code2Wav shares the Talker's card.
+        updates={"stages": {2: {"devices": "1"}}},
+    )
+]
 
 # Create parameter combinations for model and stage config
 test_params = [

tests/engine/test_omni_request.py

@@ -13,15 +13,13 @@ substitutable with the base class — including base-style calls that pass
 
 import inspect
 
-import msgspec
 import numpy as np
 import pytest
 import torch
 from vllm.sampling_params import SamplingParams
-from vllm.v1.engine import EngineCoreRequest
 from vllm.v1.request import Request
 
-from vllm_omni.engine import OmniEngineCoreRequest, PromptEmbedsPayload
+from vllm_omni.engine import PromptEmbedsPayload
 from vllm_omni.request import OmniRequest, OmniStreamingUpdate
 
 pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
@@ -113,24 +111,3 @@ def test_model_intermediate_buffer_round_trips_to_streaming_update():
     assert update is not None
     assert request.model_intermediate_buffer is buffer
     assert update.model_intermediate_buffer is buffer
-
-
-@pytest.mark.parametrize("session_id", [None, "session"])
-def test_session_survives_omni_upgrade_wire_transport_and_scheduler_conversion(session_id):
-    core = EngineCoreRequest(
-        request_id="session-request",
-        prompt_token_ids=[1, 2],
-        mm_features=None,
-        sampling_params=SamplingParams(max_tokens=2),
-        pooling_params=None,
-        arrival_time=0.0,
-        lora_request=None,
-        cache_salt=None,
-        data_parallel_rank=None,
-        session_id=session_id,
-    )
-    upgraded = OmniEngineCoreRequest.from_request(core)
-    decoded = msgspec.msgpack.decode(msgspec.msgpack.encode(upgraded), type=OmniEngineCoreRequest)
-    scheduled = OmniRequest.from_engine_core_request(decoded, block_hasher=None)
-    assert decoded.session_id == session_id
-    assert scheduled.session_id == session_id

vllm_omni/engine/__init__.py

@@ -123,7 +123,6 @@ class OmniEngineCoreRequest(EngineCoreRequest):
             trace_headers=request.trace_headers,
             resumable=request.resumable,
             external_req_id=request.external_req_id,
-            session_id=request.session_id,
             reasoning_ended=request.reasoning_ended,
             reasoning_parser_kwargs=request.reasoning_parser_kwargs,
             abort_immediately=request.abort_immediately,