diff --git a/test/srt/run_suite.py b/test/srt/run_suite.py
index 00adfa318..4746d97bc 100644
--- a/test/srt/run_suite.py
+++ b/test/srt/run_suite.py
@@ -146,7 +146,6 @@ suites = {
         TestFile("test_data_parallelism.py", 73),
         TestFile("test_dp_attention.py", 137),
         TestFile("test_mla_tp.py", 170),
-        TestFile("test_moe_ep.py", 181),
         TestFile("test_patch_torch.py", 19),
         TestFile("test_update_weights_from_distributed.py", 103),
         TestFile("test_release_memory_occupation.py", 44),
@@ -175,6 +174,7 @@ suites = {
         TestFile("test_disaggregation.py", 270),
         TestFile("test_disaggregation_different_tp.py", 155),
         TestFile("test_full_deepseek_v3.py", 463),
+        TestFile("test_moe_ep.py", 181),
     ],
     "per-commit-8-gpu-amd": [
         TestFile("test_full_deepseek_v3.py", 250),
diff --git a/test/srt/test_bench_serving.py b/test/srt/test_bench_serving.py
index 3626ed81e..19936c574 100644
--- a/test/srt/test_bench_serving.py
+++ b/test/srt/test_bench_serving.py
@@ -194,7 +194,7 @@ class TestBenchServing(CustomTestCase):
                 self.assertLess(res["median_ttft_ms"], 150)
                 # TODO: not set yet, need AMD machine
             else:
-                self.assertLess(res["median_ttft_ms"], 98)
+                self.assertLess(res["median_ttft_ms"], 100)
             self.assertLess(res["median_itl_ms"], 8)
 
     def test_online_latency_eagle(self):