[V1] Eagerly remove finished requests from the batch (#14388)

Signed-off-by: Nick Hill <nhill@redhat.com>

vllm/v1/engine/core.py

@@ -153,7 +153,9 @@ class EngineCore:
     def step(self) -> EngineCoreOutputs:
         """Schedule, execute, and make output."""
 
-        if not self.scheduler.has_unfinished_requests():
+        # Check for any requests remaining in the scheduler - unfinished,
+        # or finished and not yet removed from the batch.
+        if not self.scheduler.has_requests():
             return EngineCoreOutputs(
                 outputs=[],
                 scheduler_stats=self.scheduler.make_stats(),
@@ -335,7 +337,7 @@ class EngineCoreProc(EngineCore):
         # Loop until process is sent a SIGINT or SIGTERM
         while True:
             # 1) Poll the input queue until there is work to do.
-            while not self.scheduler.has_unfinished_requests():
+            while not self.scheduler.has_requests():
                 logger.debug("EngineCore busy loop waiting.")
                 req = self.input_queue.get()
                 self._handle_client_request(*req)