diff --git a/vllm_ascend/patch/platform/patch_balance_schedule.py b/vllm_ascend/patch/platform/patch_balance_schedule.py index 9a2cc722..abcc8d9f 100644 --- a/vllm_ascend/patch/platform/patch_balance_schedule.py +++ b/vllm_ascend/patch/platform/patch_balance_schedule.py @@ -266,7 +266,7 @@ class BalanceScheduler(Scheduler): if len(self.running) == self.max_num_running_reqs: break - balance_flag = max(t.item() for t in self.balance_queue) >= self.max_num_running_reqs - 1 + balance_flag = max(t.item() for t in self.balance_queue) == self.max_num_running_reqs if balance_flag: break