[BugFix] Fix the issue of thinker requests being preempted, causing shape mismatch. (#3147)

Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>

tests/e2e/online_serving/test_qwen3_omni_expansion.py

@@ -44,7 +44,7 @@ def get_batch_token_config(default_path):
     return modify_stage_config(
         default_path,
         updates={
-            "stages": {1: {"max_num_batched_tokens": 64}},
+            "stages": {0: {"max_num_batched_tokens": 64}, 1: {"max_num_batched_tokens": 64}},
         },
     )
 
@@ -95,7 +95,12 @@ test_params = [
 
 test_token_params = [
     pytest.param(
-        OmniServerParams(model=model, stage_config_path=get_batch_token_config(default_path), use_stage_cli=True),
+        OmniServerParams(
+            model=model,
+            stage_config_path=get_batch_token_config(default_path),
+            use_stage_cli=True,
+            server_args=["--async-chunk"],
+        ),
         id="batch_token_64",
     )
 ]