fix mapping (#3320)

Author: gzy19990617

fastdeploy/rl/rollout_model.py

@@ -89,6 +89,7 @@ def __init__(
         super(BaseRLModel, self).__init__()
         self.infer_to_train_mapping = {}
         self.fd_config = None
+        self._mappings_built = False
 
     @classmethod
     def name(cls) -> str:
@@ -145,6 +146,12 @@ def name(self) -> str:
 
     def get_name_mappings_to_training(self, trainer_degree=None) -> Dict[str, str]:
         """Generate mapping between inference and training parameter for RL(donot delete!)."""
+        if self._mappings_built:
+            return self.infer_to_train_mapping
+
+        self.infer_to_train_mapping = {}
+        self._mappings_built = True
+
         # Prepare placeholders
         place_holders = ["weight"]
 
@@ -218,6 +225,11 @@ def name(self) -> str:
 
     def get_name_mappings_to_training(self, trainer_degree=None) -> Dict[str, str]:
         """Generate mapping between inference and training parameter for RL(donot delete!)."""
+        if self._mappings_built:
+            return self.infer_to_train_mapping
+
+        self.infer_to_train_mapping = {}
+        self._mappings_built = True
         # Prepare placeholders
         place_holders = ["weight"]
 
@@ -319,6 +331,11 @@ def name(self) -> str:
 
     def get_name_mappings_to_training(self, trainer_degree=None) -> Dict[str, str]:
         """Generate mapping between inference and training parameter for RL(donot delete!)."""
+        if self._mappings_built:
+            return self.infer_to_train_mapping
+
+        self.infer_to_train_mapping = {}
+        self._mappings_built = True
         # Prepare placeholders
         place_holders = ["weight"]
 
@@ -363,6 +380,11 @@ def name(self) -> str:
 
     def get_name_mappings_to_training(self, trainer_degree=None) -> Dict[str, str]:
         """Generate mapping between inference and training parameter for RL(donot delete!)."""
+        if self._mappings_built:
+            return self.infer_to_train_mapping
+
+        self.infer_to_train_mapping = {}
+        self._mappings_built = True
         # Prepare placeholders
         place_holders = ["weight"]
 
@@ -432,6 +454,11 @@ def name(self) -> str:
         return "Qwen3ForCausalLMRL"
 
     def get_name_mappings_to_training(self, trainer_degree=None) -> Dict[str, str]:
+        if self._mappings_built:
+            return self.infer_to_train_mapping
+
+        self.infer_to_train_mapping = {}
+        self._mappings_built = True
         # Prepare placeholders
         place_holders = ["weight"]