Revert "drop ascend scheduler" (#4580)

Reverts vllm-project/vllm-ascend#4498
- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2

tests/e2e/310p/test_offline_inference_parallel_310p.py

@@ -24,12 +24,15 @@ from tests.e2e.conftest import VllmRunner
 MODELS = [
     "IntervitensInc/pangu-pro-moe-model",
 ]
-# set additional config for torchair graph
+# set additional config for ascend scheduler and torchair graph
 ADDITIONAL_CONFIG = [{
     "additional_config": {
         "torchair_graph_config": {
             "enabled": True
         },
+        "ascend_scheduler_config": {
+            "enabled": True,
+        }
     }
 }]