Remove unused kwargs from model definitions (#13555)

vllm/model_executor/models/llava.py

@@ -15,7 +15,6 @@ from transformers import __version__ as TRANSFORMERS_VERSION
 from transformers.models.llava import LlavaProcessor
 from transformers.models.pixtral import PixtralProcessor
 
-from vllm.attention import AttentionMetadata
 from vllm.config import VllmConfig
 from vllm.inputs import InputProcessingContext
 from vllm.model_executor.layers.activation import get_act_fn
@@ -658,8 +657,6 @@ class LlavaForConditionalGeneration(nn.Module, SupportsMultiModal, 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,
         **kwargs: object,
@@ -712,8 +709,6 @@ class LlavaForConditionalGeneration(nn.Module, SupportsMultiModal, SupportsPP):
 
         hidden_states = self.language_model.model(input_ids,
                                                   positions,
-                                                  kv_caches,
-                                                  attn_metadata,
                                                   intermediate_tensors,
                                                   inputs_embeds=inputs_embeds)