Fix: seamless integration with 🤗 generation pipelines

llava_qwen.py

@@ -2186,6 +2186,7 @@ class LlavaQwen2ForCausalLM(Qwen2ForCausalLM, LlavaMetaForCausalLM):
     ) -> Union[GenerateOutput, torch.LongTensor]:
         position_ids = kwargs.pop("position_ids", None)
         attention_mask = kwargs.pop("attention_mask", None)
+        inputs = kwargs.pop("input_ids", inputs)
         if "inputs_embeds" in kwargs:
             raise NotImplementedError("`inputs_embeds` is not supported")