[FEAT] support multi-stage deployment (#2396)

Signed-off-by: ZhengWG <zwg0606@gmail.com>
Signed-off-by: Zheng Wengang <zwg0606@gmail.com>
Signed-off-by: Peiqi Yin <60515999+yinpeiqi@users.noreply.github.com>
Signed-off-by: yinpe <11810305@mail.sustech.edu.cn>
Signed-off-by: yinpeiqi <yinpeiqi809@gmail.com>
Co-authored-by: Peiqi Yin <60515999+yinpeiqi@users.noreply.github.com>
Co-authored-by: yinpe <11810305@mail.sustech.edu.cn>
Co-authored-by: yinpeiqi <yinpeiqi809@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
Co-authored-by: Chenguang Zheng <645327136@qq.com>

tests/engine/test_cfg_companion_tracker.py

@@ -1,7 +1,6 @@
 import pytest
 
 from vllm_omni.engine.cfg_companion_tracker import CfgCompanionTracker
-from vllm_omni.inputs.data import OmniDiffusionSamplingParams
 
 pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
 
@@ -25,18 +24,6 @@ def test_register_companion_and_cleanup():
     assert tracker.get_companion_request_ids("req1") == {}
 
 
-def test_attach_cfg_request_ids_clones_diffusion_params():
-    tracker = CfgCompanionTracker()
-    tracker.register_companion("req1", "cfg_text", "req1__cfg_text")
-
-    params = OmniDiffusionSamplingParams()
-    updated = tracker.attach_cfg_request_ids("req1", params)
-
-    assert updated is not params
-    assert params.cfg_kv_request_ids is None
-    assert updated.cfg_kv_request_ids == {"cfg_text": "req1__cfg_text"}
-
-
 def test_abort_parent_expands_to_companions_and_cleans_up_deferred_parent():
     tracker = CfgCompanionTracker()
     tracker.register_companion("req1", "cfg_text", "req1__cfg_text")