optimum/intel/openvino/modeling_visual_language.py [2544:2575]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        **kwargs,
    ):
        # Overwritten -- in specific circumstances we don't want to forward image inputs to the model
        if past_key_values is not None:
            if inputs_embeds is not None and input_ids.shape[1] == 0:  # Exception 4
                inputs_embeds = inputs_embeds[:, -cache_position.shape[0] :]
            elif inputs_embeds is not None:
                input_ids = input_ids[:, -cache_position.shape[0] :]
            elif input_ids.shape[1] != cache_position.shape[0]:  # Default case (the "else", a no op, is Exception 2)
                input_ids = input_ids[:, cache_position]

        if cache_position[0] != 0:
            pixel_values = None
            pixel_values_videos = None

        # if `inputs_embeds` are passed, we only want to use them in the 1st generation step
        if inputs_embeds is not None and len(cache_position) == inputs_embeds.shape[1]:
            model_inputs = {"inputs_embeds": inputs_embeds, "input_ids": None}
        else:
            model_inputs = {"input_ids": input_ids, "inputs_embeds": None}

        model_inputs.update(
            {
                "position_ids": position_ids,
                "past_key_values": past_key_values,
                "use_cache": use_cache,
                "attention_mask": attention_mask,
                "pixel_values": pixel_values,
                "pixel_values_videos": pixel_values_videos,
                "image_grid_thw": image_grid_thw,
                "video_grid_thw": video_grid_thw,
                "cache_position": cache_position,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/intel/openvino/modeling_visual_language.py [3101:3131]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        **kwargs,
    ):
        if past_key_values is not None:
            if inputs_embeds is not None and input_ids.shape[1] == 0:
                inputs_embeds = inputs_embeds[:, -cache_position.shape[0] :]
            elif inputs_embeds is not None:
                input_ids = input_ids[:, -cache_position.shape[0] :]
            elif input_ids.shape[1] != cache_position.shape[0]:  # Default case (the "else", a no op, is Exception 2)
                input_ids = input_ids[:, cache_position]

        if cache_position[0] != 0:
            pixel_values = None
            pixel_values_videos = None

        # if `inputs_embeds` are passed, we only want to use them in the 1st generation step
        if inputs_embeds is not None and len(cache_position) == inputs_embeds.shape[1]:
            model_inputs = {"inputs_embeds": inputs_embeds, "input_ids": None}
        else:
            model_inputs = {"input_ids": input_ids, "inputs_embeds": None}

        model_inputs.update(
            {
                "position_ids": position_ids,
                "past_key_values": past_key_values,
                "use_cache": use_cache,
                "attention_mask": attention_mask,
                "pixel_values": pixel_values,
                "pixel_values_videos": pixel_values_videos,
                "image_grid_thw": image_grid_thw,
                "video_grid_thw": video_grid_thw,
                "cache_position": cache_position,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -