[Bugfix] If chunked_prefill is disabled, end the scheduling early. (#28911)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>

vllm/v1/core/sched/scheduler.py

@@ -508,9 +508,9 @@ class Scheduler(SchedulerInterface):
                         not self.scheduler_config.enable_chunked_prefill
                         and num_new_tokens > token_budget
                     ):
-                        self.waiting.pop_request()
-                        skipped_waiting_requests.prepend_request(request)
-                        continue
+                        # If chunked_prefill is disabled,
+                        # we can stop the scheduling here.
+                        break
 
                     num_new_tokens = min(num_new_tokens, token_budget)
                     assert num_new_tokens > 0