Caching Past Key values of any length for Vision LLM's

### Feature request Allowing passing past key values during the forward pass of more than one token similar to the text large language models. ### Motivation According to the documentation [here](https://huggingface.co/docs/transformers/en/model_doc/llava_next#transformers.LlavaNextForConditionalGeneration.forward.past_key_values) one could in theory pass past key values of the prompt to speed up the forward pass. However, I think that the cached forward pass only happens when the input_ids has **only** one new token as described in the condition [here](https://github.com/huggingface/transformers/blob/573565e35a5cc68f6cfb6337f5a93753ab16c65b/src/transformers/models/llava_next/modeling_llava_next.py#L816). Changes to this making it consistent with the text LLMs (thanks for that) would be highly appreciated. ### Your contribution If you can give me any pointers on how I can realign cache, create the attention masks, etc., It would also be very helpful