[cherry-pick][release/v0.18.0.post1] cherry-pick #2847 #2780 #2840 #2876 #2877 (#2878)

Signed-off-by: david6666666 <530634352@qq.com>
Signed-off-by: David Chen <530634352@qq.com>
Signed-off-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>

tests/entrypoints/openai_api/test_image_server.py

@@ -171,7 +171,7 @@ def test_client(mock_async_diffusion):
     app.state.stage_configs = [SimpleNamespace(stage_type="diffusion")]
     app.state.diffusion_model_name = "Qwen/Qwen-Image"  # For models endpoint
     app.state.args = Namespace(
-        default_sampling_params='{"0": {"num_inference_steps":4, "guidance_scale":7.5}}',
+        default_sampling_params='{"0": {"num_inference_steps":4, "guidance_scale":7.5, "generator_device":"cpu"}}',
         max_generated_image_size=1024 * 1792,
     )
 
@@ -194,7 +194,7 @@ def async_omni_test_client():
         SimpleNamespace(stage_type="diffusion"),
     ]
     app.state.args = Namespace(
-        default_sampling_params='{"1": {"num_inference_steps":4, "guidance_scale":7.5}}',
+        default_sampling_params='{"1": {"num_inference_steps":4, "guidance_scale":7.5, "generator_device":"cpu"}}',
         max_generated_image_size=1048576,  # 1024*1024 to support resolution tests
     )
     return TestClient(app)
@@ -216,7 +216,7 @@ def async_omni_rgba_test_client():
         SimpleNamespace(stage_type="diffusion"),
     ]
     app.state.args = Namespace(
-        default_sampling_params='{"1": {"num_inference_steps":4, "guidance_scale":7.5}}',
+        default_sampling_params='{"1": {"num_inference_steps":4, "guidance_scale":7.5, "generator_device":"cpu"}}',
         max_generated_image_size=1048576,
     )
     return TestClient(app)
@@ -238,7 +238,7 @@ def async_omni_stage_configs_only_client():
     # Intentionally do not populate app.state.stage_configs. Refactored
     # AsyncOmni exposes stage_configs on the engine instance.
     app.state.args = Namespace(
-        default_sampling_params='{"1": {"num_inference_steps":4, "guidance_scale":7.5}}',
+        default_sampling_params='{"1": {"num_inference_steps":4, "guidance_scale":7.5, "generator_device":"cpu"}}',
         max_generated_image_size=1024 * 1792,
     )
     return TestClient(app)
@@ -776,6 +776,63 @@ def test_image_edit_rejects_multiple_images_when_model_does_not_support_them(asy
     assert engine.captured_prompt is None
 
 
+def test_image_edit_rejects_too_many_images_for_qwen_image_edit_2511(async_omni_test_client):
+    engine = async_omni_test_client.app.state.engine_client
+    engine.get_diffusion_od_config = lambda: SimpleNamespace(
+        supports_multimodal_inputs=True,
+        max_multimodal_image_inputs=4,
+    )
+
+    response = async_omni_test_client.post(
+        "/v1/images/edits",
+        files=[
+            ("image", make_test_image_bytes((16, 16))),
+            ("image", make_test_image_bytes((16, 16))),
+            ("image", make_test_image_bytes((16, 16))),
+            ("image", make_test_image_bytes((16, 16))),
+            ("image", make_test_image_bytes((16, 16))),
+        ],
+        data={"prompt": "hello world."},
+    )
+
+    assert response.status_code == 400
+    assert response.json()["detail"] == "Received 5 input images. At most 4 images are supported by this model."
+    assert engine.captured_prompt is None
+
+
+def test_image_edit_rejects_too_many_images_for_qwen_image_edit_2511_before_loading(
+    async_omni_test_client, monkeypatch: pytest.MonkeyPatch
+):
+    import vllm_omni.entrypoints.openai.api_server as api_server_module
+
+    engine = async_omni_test_client.app.state.engine_client
+    engine.get_diffusion_od_config = lambda: SimpleNamespace(
+        supports_multimodal_inputs=True,
+        max_multimodal_image_inputs=4,
+    )
+
+    def _fail_load(*args, **kwargs):
+        raise AssertionError("_load_input_images should not run for over-limit requests")
+
+    monkeypatch.setattr(api_server_module, "_load_input_images", _fail_load)
+
+    response = async_omni_test_client.post(
+        "/v1/images/edits",
+        files=[
+            ("image", make_test_image_bytes((16, 16))),
+            ("image", make_test_image_bytes((16, 16))),
+            ("image", make_test_image_bytes((16, 16))),
+            ("image", make_test_image_bytes((16, 16))),
+            ("image", make_test_image_bytes((16, 16))),
+        ],
+        data={"prompt": "hello world."},
+    )
+
+    assert response.status_code == 400
+    assert response.json()["detail"] == "Received 5 input images. At most 4 images are supported by this model."
+    assert engine.captured_prompt is None
+
+
 def test_image_edit_parameter_pass(async_omni_test_client):
     img_bytes_1 = make_test_image_bytes((16, 16))
 
@@ -954,6 +1011,7 @@ def test_image_edit_parameter_default(async_omni_test_client):
     assert captured_sampling_params.num_outputs_per_prompt == 1
     assert captured_sampling_params.num_inference_steps == 4
     assert captured_sampling_params.guidance_scale == 7.5
+    assert captured_sampling_params.generator_device == "cpu"
 
     # Test that a size exceeding max_generated_image_size returns 400
     response = async_omni_test_client.post(
@@ -987,6 +1045,7 @@ def test_image_edit_parameter_default_single_stage(test_client):
     assert captured_sampling_params.num_outputs_per_prompt == 1
     assert captured_sampling_params.num_inference_steps == 4
     assert captured_sampling_params.guidance_scale == 7.5
+    assert captured_sampling_params.generator_device == "cpu"
 
     # Size exceeding max_generated_image_size (1024*1792) returns 400
     response = test_client.post(

tests/entrypoints/openai_api/test_video_api_utils.py

@@ -87,7 +87,9 @@ def test_encode_video_bytes_without_audio_uses_diffusers_export(monkeypatch):
     _install_fake_export_to_video(monkeypatch, export_calls)
     monkeypatch.setattr(
         "vllm_omni.diffusion.utils.media_utils.mux_video_audio_bytes",
-        lambda *args, **kwargs: (_ for _ in ()).throw(AssertionError("no-audio path should not use mux_video_audio_bytes")),
+        lambda *args, **kwargs: (_ for _ in ()).throw(
+            AssertionError("no-audio path should not use mux_video_audio_bytes")
+        ),
     )
 
     video = np.linspace(0.0, 1.0, num=4 * 2 * 2 * 3, dtype=np.float32).reshape(4, 2, 2, 3)
@@ -123,7 +125,7 @@ def test_frame_interpolator_runs_actual_torch_tensor_path(monkeypatch):
     assert torch.isfinite(output_video).all()
 
 
-def test_frame_interpolator_prefers_input_tensor_device(monkeypatch):
+def test_frame_interpolator_uses_platform_device_when_tensor_is_cpu(monkeypatch):
     chosen_devices = []
     model = rife_interpolator.Model().eval()
 
@@ -134,10 +136,11 @@ def test_frame_interpolator_prefers_input_tensor_device(monkeypatch):
     interpolator = rife_interpolator.FrameInterpolator()
     monkeypatch.setattr(interpolator, "_ensure_model_loaded", _fake_ensure_model_loaded)
     monkeypatch.setattr(model.flownet, "to", lambda device: model.flownet)
+    monkeypatch.setattr(rife_interpolator, "_select_torch_device", lambda: torch.device("cuda"))
 
     video = torch.zeros(1, 3, 2, 32, 32)
     output_video, multiplier = interpolator.interpolate_tensor(video, exp=1, scale=1.0)
 
-    assert chosen_devices == [video.device]
+    assert chosen_devices == [torch.device("cuda")]
     assert multiplier == 2
     assert output_video.shape == (1, 3, 3, 32, 32)

tests/entrypoints/openai_api/test_video_server.py

@@ -14,8 +14,7 @@ import time
 from types import SimpleNamespace
 
 import pytest
-from fastapi import FastAPI
-from fastapi import HTTPException
+from fastapi import FastAPI, HTTPException
 from fastapi.testclient import TestClient
 from PIL import Image
 from pytest_mock import MockerFixture
@@ -981,5 +980,3 @@ async def test_run_generation_maps_omni_request_error_to_http_exception():
         "error_type": "OutOfMemoryError",
         "detail": {"retryable": False},
     }
-
-