[Feat] support CFG Parallel for FLUX kontext (#2281)

Signed-off-by: Lancer <maruixiang6688@gmail.com>

tests/e2e/online_serving/test_flux_kontext_expansion.py

@@ -5,6 +5,8 @@ and are supported by the FluxKontext model.
 
 import pytest
 
+from tests.helpers import skip_if_gated_repo_inaccessible
+from tests.helpers.mark import hardware_marks
 from tests.helpers.media import generate_synthetic_image
 from tests.helpers.runtime import OmniServer, OmniServerParams, OpenAIClientHandler, dummy_messages_from_mix_data
 
@@ -13,6 +15,8 @@ pytestmark = [pytest.mark.diffusion, pytest.mark.slow]
 EDIT_PROMPT = "Transform this modern, geometrist image into a Vincent van Gogh style impressionist painting."
 NEGATIVE_PROMPT = "blurry, low quality, modern, geometrist"
 MODEL = "black-forest-labs/FLUX.1-Kontext-dev"
+skip_if_gated_repo_inaccessible(MODEL)
+PARALLEL_FEATURE_MARKS = hardware_marks(res={"cuda": "L4"}, num_cards=2)
 
 
 def _get_diffusion_feature_cases(model: str):
@@ -26,7 +30,20 @@ def _get_diffusion_feature_cases(model: str):
                     "--enable-cpu-offload",
                 ],
             ),
-            id="parallel_001",
+            id="parallel_tp_2",
+            marks=PARALLEL_FEATURE_MARKS,
+        ),
+        pytest.param(
+            OmniServerParams(
+                model=model,
+                server_args=[
+                    "--enable-cpu-offload",
+                    "--cfg-parallel-size",
+                    "2",
+                ],
+            ),
+            id="parallel_cfg_2",
+            marks=PARALLEL_FEATURE_MARKS,
         ),
     ]