[Core] Support reseting all running requests' KV while calling reset_prefix_cache (#28827)

Signed-off-by: Zhuohan Li <zhuohan123@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>

vllm/v1/engine/core.py

@@ -483,8 +483,8 @@ class EngineCore:
 
         self.model_executor.reset_mm_cache()
 
-    def reset_prefix_cache(self):
-        self.scheduler.reset_prefix_cache()
+    def reset_prefix_cache(self, reset_running_requests: bool = False) -> bool:
+        return self.scheduler.reset_prefix_cache(reset_running_requests)
 
     def sleep(self, level: int = 1):
         self.model_executor.sleep(level)