[MM] Skip VMM error gathers for text-only requests (#40005)

Co-authored-by: metamergebot <324680979+metamergebot@users.noreply.github.com>
Co-authored-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>

test/registered/unit/multimodal/test_gpu_feature_transport.py

@@ -9,6 +9,7 @@ from unittest.mock import AsyncMock, MagicMock, call, patch
 import torch
 
 from sglang.test.ci.ci_register import register_cpu_ci
+from sglang.test.test_utils import CustomTestCase
 
 register_cpu_ci(est_time=11, suite="base-a-test-cpu")
 
@@ -760,7 +761,7 @@ class TestCudaVmmFeatureTransport(unittest.TestCase):
         self.assertIs(transport.pool, pool)
 
 
-class TestSchedulerMmTransportBoundary(unittest.TestCase):
+class TestSchedulerMmTransportBoundary(CustomTestCase):
     def _publish(self, **fields):
         from sglang.srt.runtime_context import get_context