[BugFix][P/D] Modify the recalculation logic to prevent waiting requests from filling up the D node KVCache (#3641)

### What this PR does / why we need it?
Modify the recalculation logic to prevent waiting requests from filling
up the D node KVCache

- vLLM version: v0.11.0rc3
- vLLM main:
17c540a993

Signed-off-by: underfituu <hzhucong@163.com>

vllm_ascend/core/recompute_scheduler.py

@@ -362,7 +362,7 @@ class RecomputeScheduler(SchedulerInterface):
         skipped_waiting_requests = create_request_queue(self.policy)
 
         # Next, schedule the WAITING requests.
-        if not preempted_reqs:
+        if not preempted_reqs and not recomputed_reqs:
             while self.waiting and token_budget > 0:
                 if len(self.running) == self.max_num_running_reqs:
                     break