[Rebase] Rebase to vllm releases/v0.22.0 (#3891)

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: ZhengWG <zwg0606@gmail.com>
Signed-off-by: david6666666 <530634352@qq.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Signed-off-by: nainiu258 <cperfect02@163.com>
Signed-off-by: nainiu258 <101917677+nainiu258@users.noreply.github.com>
Signed-off-by: JasonJ2021 <jasonj@zju.edu.cn>
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: skf <54565339+skf-1999@users.noreply.github.com>
Co-authored-by: Zheng Wengang <zwg0606@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: nainiu258 <101917677+nainiu258@users.noreply.github.com>
Co-authored-by: Jason <72191212+JasonJ2021@users.noreply.github.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>

tests/diffusion/offloader/test_diffusion_cpu_offload.py

@@ -17,7 +17,7 @@ AUDIO_MODEL = {
 }
 
 IMAGE_VIDEO_MODELS = {
-    "riverclouds/qwen_image_random": {"cuda": 2500, "rocm": 2100},
+    "riverclouds/qwen_image_random": {"cuda": 2200, "rocm": 2100},
 }
 
 MODELS = {**AUDIO_MODEL, **IMAGE_VIDEO_MODELS}

tests/diffusion/test_diffusion_model_runner.py

@@ -301,8 +301,4 @@ def test_vllm_set_forward_context_implementation(monkeypatch):
                 "vllm_config",
             ),
         ),
-        ("ir_op_priority", None),
-        ("enable_torch_wrap", vllm_config.compilation_config.ir_enable_torch_wrap),
-        ("enable_torch_wrap_exit", vllm_config.compilation_config.ir_enable_torch_wrap),
-        ("ir_op_priority_exit", None),
     ], ERROR_MESSAGE

tests/diffusion/test_stage_diffusion_proc.py

@@ -85,7 +85,7 @@ class MockOmniRequestOutput:
 BASE_HEIGHT = 512
 BASE_WIDTH = 512
 BASE_INFER_STEPS = 10
-DELAY_BASE = 2
+DELAY_BASE = 0.01
 
 
 class MockDiffusionEngine:
@@ -93,7 +93,7 @@ class MockDiffusionEngine:
         def simulate_step_delay(height, width, num_inference_steps) -> float:
             return (height / BASE_HEIGHT) * (width / BASE_WIDTH) * (num_inference_steps / BASE_INFER_STEPS)
 
-        DELAY_BASE = 2
+        DELAY_BASE = 0.01
         delay_scale = simulate_step_delay(
             request.sampling_params.height, request.sampling_params.width, request.sampling_params.num_inference_steps
         )
@@ -139,7 +139,7 @@ async def test_proc_process_request_with_batching_async_output():
     assert len(results) == len(test_requests)
     base_time = DELAY_BASE
     time_gap_std = DELAY_BASE * 2 * 2 * 1  # height/width/steps infer time scale
-    eps = 0.5
+    eps = 0.1
     for i, (res, elapsed_time) in enumerate(results):
         assert res.request_id == test_requests[i]["request_id"]
         assert isinstance(res, MockOmniRequestOutput)