Remove unused kwargs from model definitions (#13555)

vllm/model_executor/models/qwen2_rm.py

@@ -5,12 +5,11 @@
 # Copyright 2024 The Qwen team.
 # Copyright 2023 The vLLM team.
 """Inference-only Qwen2-RM model compatible with HuggingFace weights."""
-from typing import Iterable, List, Optional, Set, Tuple, Union
+from typing import Iterable, Optional, Set, Tuple, Union
 
 import torch
 from torch import nn
 
-from vllm.attention import AttentionMetadata
 from vllm.config import VllmConfig
 from vllm.model_executor.layers.linear import (ColumnParallelLinear,
                                                RowParallelLinear)
@@ -80,13 +79,10 @@ class Qwen2RewardBaseModel(nn.Module, SupportsLoRA, SupportsPP):
         self,
         input_ids: torch.Tensor,
         positions: torch.Tensor,
-        kv_caches: List[torch.Tensor],
-        attn_metadata: AttentionMetadata,
         intermediate_tensors: Optional[IntermediateTensors] = None,
         inputs_embeds: Optional[torch.Tensor] = None,
     ) -> Union[torch.Tensor, IntermediateTensors]:
-        hidden_states = self.model(input_ids, positions, kv_caches,
-                                   attn_metadata, intermediate_tensors,
+        hidden_states = self.model(input_ids, positions, intermediate_tensors,
                                    inputs_embeds)
         logits, _ = self.score(hidden_states)
         return logits