diff --git a/vllm_ascend/patch/platform/__init__.py b/vllm_ascend/patch/platform/__init__.py
index 1e4e5b49..d304af1c 100644
--- a/vllm_ascend/patch/platform/__init__.py
+++ b/vllm_ascend/patch/platform/__init__.py
@@ -19,7 +19,8 @@ import os
 import vllm_ascend.patch.platform.patch_distributed  # noqa
 import vllm_ascend.patch.platform.patch_fusion_matcher_compat_ops  # noqa
 import vllm_ascend.patch.platform.patch_kv_cache_interface  # noqa
-from vllm_ascend.utils import is_310p
+from vllm_ascend import envs
+from vllm_ascend.utils import is_310p, vllm_version_is
 
 if not is_310p():
     import vllm_ascend.patch.platform.patch_mamba_config  # noqa
@@ -31,3 +32,5 @@ import vllm_ascend.patch.platform.patch_torch_accelerator  # noqa
 
 if os.getenv("DYNAMIC_EPLB", "false").lower() in ("true", "1") or os.getenv("EXPERT_MAP_RECORD", "false") == "true":
     import vllm_ascend.patch.platform.patch_multiproc_executor  # noqa
+if envs.VLLM_ASCEND_BALANCE_SCHEDULING and vllm_version_is("0.17.0"):
+    import vllm_ascend.patch.platform.patch_balance_schedule  # noqa