[Executor] CUDAGraph support RL training (#3265)

* add clear graph opt backend

* cuda graph support rl

* add branch

* 1.fix dynamic_weight_manager bug 2.add clear api for CasualLM

* open test case

* fix typo

* update mkdocs.yaml

* [Docs]Update mkdocs.yml

* update test case

* use unittest in graph test case

fastdeploy/model_executor/graph_optimization/graph_optimization_backend.py

@@ -144,3 +144,7 @@ class GraphOptBackend:
             return self.runnable(**kwargs)
         else:
             return self.cudagraph_piecewise_backend.__call__(**kwargs)
+
+    def clear_cudagraph_piecewise_backend(self):
+        """ """
+        self.cudagraph_piecewise_backend.clear_graph()