https://github.com/huggingface/transformers/issues/29426

Author: pseudotensor

llava/model/language_model/llava_llama.py

@@ -68,6 +68,7 @@ def forward(
         images: Optional[torch.FloatTensor] = None,
         image_sizes: Optional[List[List[int]]] = None,
         return_dict: Optional[bool] = None,
+        cache_position=None,
     ) -> Union[Tuple, CausalLMOutputWithPast]:
 
         if inputs_embeds is None: