diff --git a/tests/e2e/nightly/models/test_qwen2_5_vl_32b.py b/tests/e2e/nightly/models/test_qwen2_5_vl_32b.py
index 77c1a7e1..4ecd403f 100644
--- a/tests/e2e/nightly/models/test_qwen2_5_vl_32b.py
+++ b/tests/e2e/nightly/models/test_qwen2_5_vl_32b.py
@@ -80,7 +80,7 @@ async def test_models(model: str, tp_size: int) -> None:
         "HCCL_OP_EXPANSION_MODE": "AIV"
     }
     server_args = [
-        "--no-enable-prefix-caching", "--disable-mm-preprocessor-cache",
+        "--no-enable-prefix-caching", "--mm-processor-cache-gb", "0",
         "--tensor-parallel-size",
         str(tp_size), "--port",
         str(port), "--max-model-len", "30000", "--max-num-batched-tokens",
diff --git a/tests/e2e/nightly/models/test_qwen2_5_vl_7b.py b/tests/e2e/nightly/models/test_qwen2_5_vl_7b.py
index d3a726bf..33cab210 100644
--- a/tests/e2e/nightly/models/test_qwen2_5_vl_7b.py
+++ b/tests/e2e/nightly/models/test_qwen2_5_vl_7b.py
@@ -72,7 +72,7 @@ async def test_models(model: str, tp_size: int) -> None:
         "HCCL_OP_EXPANSION_MODE": "AIV"
     }
     server_args = [
-        "--no-enable-prefix-caching", "--disable-mm-preprocessor-cache",
+        "--no-enable-prefix-caching", "--mm-processor-cache-gb", "0",
         "--tensor-parallel-size",
         str(tp_size), "--port",
         str(port), "--max-model-len", "30000", "--max-num-batched-tokens",