optimum/intel/openvino/modeling_visual_language.py [2771:2809]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def rot_pos_emb(self, grid_thw):
        pos_ids = []
        for t, h, w in grid_thw:
            hpos_ids = torch.arange(h).unsqueeze(1).expand(-1, w)
            hpos_ids = hpos_ids.reshape(
                h // self.config.vision_config.spatial_merge_size,
                self.config.vision_config.spatial_merge_size,
                w // self.config.vision_config.spatial_merge_size,
                self.config.vision_config.spatial_merge_size,
            )
            hpos_ids = hpos_ids.permute(0, 2, 1, 3)
            hpos_ids = hpos_ids.flatten()

            wpos_ids = torch.arange(w).unsqueeze(0).expand(h, -1)
            wpos_ids = wpos_ids.reshape(
                h // self.config.vision_config.spatial_merge_size,
                self.config.vision_config.spatial_merge_size,
                w // self.config.vision_config.spatial_merge_size,
                self.config.vision_config.spatial_merge_size,
            )
            wpos_ids = wpos_ids.permute(0, 2, 1, 3)
            wpos_ids = wpos_ids.flatten()
            pos_ids.append(torch.stack([hpos_ids, wpos_ids], dim=-1).repeat(t, 1))
        pos_ids = torch.cat(pos_ids, dim=0)
        max_grid_size = grid_thw[:, 1:].max()
        rotary_pos_emb_full = self._rotary_pos_emb(max_grid_size)
        rotary_pos_emb = rotary_pos_emb_full[pos_ids].flatten(1)
        return rotary_pos_emb

    def get_multimodal_embeddings(
        self,
        input_ids,
        pixel_values=None,
        attention_mask=None,
        position_ids=None,
        pixel_values_videos=None,
        image_grid_thw=None,
        video_grid_thw=None,
        cache_position=None,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/intel/openvino/modeling_visual_language.py [3137:3175]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def rot_pos_emb(self, grid_thw):
        pos_ids = []
        for t, h, w in grid_thw:
            hpos_ids = torch.arange(h).unsqueeze(1).expand(-1, w)
            hpos_ids = hpos_ids.reshape(
                h // self.config.vision_config.spatial_merge_size,
                self.config.vision_config.spatial_merge_size,
                w // self.config.vision_config.spatial_merge_size,
                self.config.vision_config.spatial_merge_size,
            )
            hpos_ids = hpos_ids.permute(0, 2, 1, 3)
            hpos_ids = hpos_ids.flatten()

            wpos_ids = torch.arange(w).unsqueeze(0).expand(h, -1)
            wpos_ids = wpos_ids.reshape(
                h // self.config.vision_config.spatial_merge_size,
                self.config.vision_config.spatial_merge_size,
                w // self.config.vision_config.spatial_merge_size,
                self.config.vision_config.spatial_merge_size,
            )
            wpos_ids = wpos_ids.permute(0, 2, 1, 3)
            wpos_ids = wpos_ids.flatten()
            pos_ids.append(torch.stack([hpos_ids, wpos_ids], dim=-1).repeat(t, 1))
        pos_ids = torch.cat(pos_ids, dim=0)
        max_grid_size = grid_thw[:, 1:].max()
        rotary_pos_emb_full = self._rotary_pos_emb(max_grid_size)
        rotary_pos_emb = rotary_pos_emb_full[pos_ids].flatten(1)
        return rotary_pos_emb

    def get_multimodal_embeddings(
        self,
        input_ids,
        pixel_values=None,
        attention_mask=None,
        position_ids=None,
        pixel_values_videos=None,
        image_grid_thw=None,
        video_grid_thw=None,
        cache_position=None,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -