[Feature] Enable prefix caching as default (#3816)

* [Feature] Enable prefix caching as default

* [Feature] Enable prefix caching as default

* Set prefix caching as default

* skip dynamic load

* fix kill bug

* fix kill bug

* fix kill bug

* fix ci

* fix

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>

tests/ce/deploy/deploy.py

@@ -181,6 +181,19 @@ def stop_server(signum=None, frame=None):
     except Exception as e:
         print(f"Failed to stop server: {e}, {str(traceback.format_exc())}")
 
+    try:
+        result = subprocess.run(
+            f"ps -ef -ww | grep {FD_CACHE_QUEUE_PORT} | grep -v grep", shell=True, capture_output=True, text=True
+        )
+        for line in result.stdout.strip().split("\n"):
+            if not line:
+                continue
+            parts = line.split()
+            pid = int(parts[1])  # ps -ef 的第二列是 PID
+            print(f"Killing PID: {pid}")
+            os.kill(pid, signal.SIGKILL)
+    except Exception as e:
+        print(f"Failed to kill cache manager process: {e}, {str(traceback.format_exc())}")
     for port in [FD_API_PORT, FD_ENGINE_QUEUE_PORT, FD_METRICS_PORT, FD_CACHE_QUEUE_PORT]:
         try:
             output = subprocess.check_output(f"lsof -i:{port} -t", shell=True).decode().strip()
@@ -285,7 +298,7 @@ def start_service():
 def switch_service():
     """切换模型服务"""
     # kill掉已有服务
-    stop_server()
+    res, status_code = stop_server()
     time.sleep(2)
 
     try: