【Feature】add fd plugins && rm model_classes (#3123)

* add fd plugins && rm model_classed

* fix reviews

* add docs

* fix

* fix unitest ci

fastdeploy/model_executor/models/qwen3moe.py

@@ -324,6 +324,10 @@ class Qwen3MoePretrainedModel(PretrainedModel):
         """
         return None
 
+    @classmethod
+    def arch_name(self):
+        return "Qwen3MoeForCausalLM"
+
     @classmethod
     def _get_tensor_parallel_mappings(cls, config, is_split=True):
         # TODO not support TP split now, next PR will support TP.