[Diffusion][HunyuanImage3] Add request paged prefix caching (#7719)

Signed-off-by: zwhzzz0821 <2831474076@qq.com>

tests/benchmarks/test_accuracy_bench_utils.py

@@ -9,6 +9,7 @@ import sys
 from pathlib import Path
 
 import pytest
+import requests
 from PIL import Image
 
 pytestmark = [pytest.mark.core_model, pytest.mark.diffusion, pytest.mark.cpu]
@@ -311,7 +312,8 @@ def test_trajectory_judge_payload_collapses_six_frames_into_single_storyboard():
     assert judge_images[0].size == (24, 12)
 
 
-def test_image_edit_client_uses_openai_image_edit_endpoint(monkeypatch):
+@pytest.mark.parametrize("num_images", [1, 2])
+def test_image_edit_client_uses_openai_image_edit_endpoint(monkeypatch, num_images):
     captured = {}
 
     class FakeResponse:
@@ -344,16 +346,46 @@ def test_image_edit_client_uses_openai_image_edit_endpoint(monkeypatch):
     output = client.generate_image_edit(
         model="Qwen/Qwen-Image-Edit",
         prompt="edit this image",
-        images=image,
+        images=image if num_images == 1 else [image] * num_images,
         width=512,
         height=512,
+        guidance_scale=2.5,
+        seed=42,
+        bot_task="think_recaption",
+        sys_type="en_unified",
     )
 
     assert output.size == (1, 1)
     assert captured["url"] == "http://127.0.0.1:8093/v1/images/edits"
     assert captured["data"]["prompt"] == "edit this image"
     assert captured["data"]["size"] == "512x512"
-    assert captured["files"][0][0] == "image"
+    assert len(captured["files"]) == num_images
+    assert all(field == ("image" if num_images == 1 else "image[]") for field, _ in captured["files"])
+    assert captured["data"]["guidance_scale"] == "2.5"
+    assert captured["data"]["seed"] == "42"
+    assert captured["data"]["bot_task"] == "think_recaption"
+    assert captured["data"]["sys_type"] == "en_unified"
+
+
+@pytest.mark.parametrize("status_code", [400, 500])
+def test_image_edit_client_preserves_server_error_detail(mocker, status_code):
+    response = requests.Response()
+    response.status_code = status_code
+    response._content = b'{"error": "image input limit exceeded"}'
+    post = mocker.patch("benchmarks.accuracy.common.requests.post", return_value=response)
+    client = VllmOmniImageClient(base_url="http://127.0.0.1:8093")
+
+    with pytest.raises(requests.HTTPError, match="image input limit exceeded") as exc:
+        client.generate_image_edit(
+            model="test-model",
+            prompt="edit this image",
+            images=Image.new("RGB", (2, 2)),
+            width=512,
+            height=512,
+        )
+
+    assert exc.value.response is response
+    post.assert_called_once()
 
 
 def test_text_to_image_client_forwards_output_compression(monkeypatch):

tests/benchmarks/test_serve_cli.py

@@ -6,6 +6,7 @@ import json
 import os
 import subprocess
 import textwrap
+import time
 from pathlib import Path
 
 import pytest
@@ -21,6 +22,76 @@ from vllm_omni.utils.tracking_parser import TrackingArgumentParser
 pytestmark = [pytest.mark.core_model, pytest.mark.cpu, pytest.mark.benchmark]
 
 
+def test_it2i_dataset_uses_upstream_warmups(monkeypatch, tmp_path):
+    """Exercise real dataset/benchmark code; replace only the HTTP backend."""
+    from vllm_omni.benchmarks import serve
+    from vllm_omni.benchmarks.patch import patch
+    from vllm_omni.entrypoints.cli.benchmark.serve import OmniBenchmarkServingSubcommand
+
+    dataset_path = Path(__file__).parents[1] / "assets/hunyuan_image3/it2i.jsonl"
+    sample = json.loads(dataset_path.read_text(encoding="utf-8"))
+    parser = argparse.ArgumentParser()
+    OmniBenchmarkServingSubcommand.add_cli_args(parser)
+    args = parser.parse_args(
+        [
+            "--model",
+            "test-model",
+            "--endpoint",
+            "/v1/images/edits",
+            "--dataset-name",
+            "custom_image",
+            "--dataset-path",
+            str(dataset_path),
+            "--skip-tokenizer-init",
+            "--disable-shuffle",
+            "--disable-tqdm",
+            "--num-prompts",
+            "8",
+            "--num-warmups",
+            "2",
+            "--max-concurrency",
+            "1",
+            "--ready-check-timeout-sec",
+            "0",
+            "--percentile-metrics",
+            "e2el",
+            "--extra-body",
+            '{"seed":42,"guidance_scale":2.5,"bot_task":"think_recaption"}',
+            "--save-result",
+            "--result-dir",
+            str(tmp_path),
+            "--result-filename",
+            "result.json",
+        ]
+    )
+    requests = []
+
+    async def request_func(request_func_input, session, pbar=None):
+        requests.append(request_func_input)
+        if pbar is not None:
+            pbar.update(1)
+        return patch.MixRequestFuncOutput(
+            success=True,
+            prompt_len=1,
+            output_tokens=1,
+            image_count=1,
+            start_time=time.perf_counter(),
+            latency=99.0 if len(requests) <= 2 else 0.1,
+        )
+
+    monkeypatch.setitem(patch.ASYNC_REQUEST_FUNCS, "/v1/images/edits", request_func)
+    result = serve.main(args)
+    assert len(requests) == 10
+    for request in requests:
+        assert request.prompt == sample["prompt"]
+        assert [image["image_url"]["url"] for image in request.multi_modal_content] == sample["image_files"]
+        assert request.extra_body == args.extra_body
+    assert result["completed"] == 8
+    saved = json.loads((tmp_path / "result.json").read_text())
+    assert saved["completed"] == 8
+    assert saved["mean_e2el_ms"] == pytest.approx(100.0)  # Excludes both 99-second warmups.
+
+
 @pytest.mark.parametrize(
     "dataset_name",
     [