[FEAT] Shared mem pool based cuda ipc for multi-modal data transport (#11917)

Co-authored-by: kousakawang <wanghanpei@bytedance.com>
Co-authored-by: Yuan Luo <4908075+yuan-luo@users.noreply.github.com>

test/srt/models/test_vlm_models.py

@@ -145,6 +145,8 @@ class TestVLMModels(CustomTestCase):
             process_env = os.environ.copy()
             if custom_env:
                 process_env.update(custom_env)
+            # if test vlm with cuda_ipc feature, open this env_var
+            process_env["SGLANG_USE_CUDA_IPC_TRANSPORT"] = "1"
 
             # Prepare stdout/stderr redirection if needed
             stdout_file = None