diff --git a/python/sglang/multimodal_gen/test/server/perf_baselines.json b/python/sglang/multimodal_gen/test/server/perf_baselines.json
index 2158b5b6a567..7fd88fd678b8 100644
--- a/python/sglang/multimodal_gen/test/server/perf_baselines.json
+++ b/python/sglang/multimodal_gen/test/server/perf_baselines.json
@@ -5,9 +5,9 @@
         "description": "Reference numbers captured from the CI diffusion server baseline run"
     },
     "tolerances": {
-        "e2e": 0.05,
+        "e2e": 0.1,
         "denoise_stage": 0.05,
-        "non_denoise_stage": 0.3,
+        "non_denoise_stage": 0.4,
         "denoise_step": 0.2,
         "denoise_agg": 0.08
     },
@@ -41,7 +41,7 @@
                 "TimestepPreparationStage": 10.6,
                 "LatentPreparationStage": 11.8,
                 "DenoisingStage": 21202.6,
-                "DecodingStage": 512.6
+                "DecodingStage": 751.1
             },
             "denoise_step_ms": {
                 "0": 1077.77,
@@ -297,7 +297,6 @@
             "expected_avg_denoise_ms": 1820.02,
             "expected_median_denoise_ms": 1798.65
         },
-
         "wan2_2_ti2v_5b": {
             "stages_ms": {
                 "InputValidationStage": 96.27,
@@ -387,26 +386,25 @@
         },
         "fast_hunyuan_video": {
             "stages_ms": {
-                "InputValidationStage": 0.07,
-                "TextEncodingStage": 598.66,
-                "ConditioningStage": 0.01,
-                "TimestepPreparationStage": 57.26,
-                "LatentPreparationStage": 15.38,
-                "DenoisingStage": 3367.01,
-                "DecodingStage": 2457.57,
-                "per_frame_generation": null
+                "InputValidationStage": 0.09,
+                "TextEncodingStage": 845.64,
+                "ConditioningStage": 0.04,
+                "TimestepPreparationStage": 125.22,
+                "LatentPreparationStage": 29.34,
+                "DenoisingStage": 3860.64,
+                "DecodingStage": 2580.55
             },
             "denoise_step_ms": {
-                "0": 1577.86,
-                "1": 161.04,
-                "2": 406.81,
-                "3": 408.67,
-                "4": 403.55,
-                "5": 405.31
+                "0": 2063.08,
+                "1": 164.02,
+                "2": 406.99,
+                "3": 407.95,
+                "4": 407.51,
+                "5": 404.2
             },
-            "expected_e2e_ms": 6521.03,
-            "expected_avg_denoise_ms": 560.54,
-            "expected_median_denoise_ms": 406.06
+            "expected_e2e_ms": 7487.87,
+            "expected_avg_denoise_ms": 642.29,
+            "expected_median_denoise_ms": 407.25
         },
         "wan2_2_i2v_a14b_2gpu": {
             "stages_ms": {
@@ -415,7 +413,7 @@
                 "ConditioningStage": 0.02,
                 "TimestepPreparationStage": 2.2,
                 "LatentPreparationStage": 8.93,
-                "ImageVAEEncodingStage":  2075.47,
+                "ImageVAEEncodingStage": 2075.47,
                 "DenoisingStage": 382628.41,
                 "DecodingStage": 2820.89
             },
diff --git a/python/sglang/multimodal_gen/test/server/test_server_perf_b.py b/python/sglang/multimodal_gen/test/server/test_server_perf_b.py
index f99b410bf14c..0faa8fc647eb 100644
--- a/python/sglang/multimodal_gen/test/server/test_server_perf_b.py
+++ b/python/sglang/multimodal_gen/test/server/test_server_perf_b.py
@@ -15,7 +15,7 @@
     diffusion_server,
 )
 from sglang.multimodal_gen.test.server.testcase_configs import (
-    ONE_GPU_CASES_A,
+    ONE_GPU_CASES_B,
     DiffusionTestCase,
 )
 
@@ -25,7 +25,7 @@
 class TestDiffusionPerformanceOneGpu(DiffusionPerformanceBase):
     """Performance tests for 1-GPU diffusion cases."""
 
-    @pytest.fixture(params=ONE_GPU_CASES_A, ids=lambda c: c.id)
+    @pytest.fixture(params=ONE_GPU_CASES_B, ids=lambda c: c.id)
     def case(self, request) -> DiffusionTestCase:
         """Provide a DiffusionTestCase for each 1-GPU test."""
         return request.param