Fix missing video inputs for PerceptionLM. (#39971)

* Fix missing video inputs for PerceptionLM.

* Minor fix for vanilla input image (only C,H,W, no tiles dim).

* Revert "Minor fix for vanilla input image (only C,H,W, no tiles dim)."

This reverts commit 181d87b.

Author: shuminghu

src/transformers/models/perception_lm/processing_perception_lm.py

@@ -170,7 +170,7 @@ def __call__(
             mm_token_type_ids[array_ids == self.image_token_id] = 1
             text_inputs["mm_token_type_ids"] = mm_token_type_ids.tolist()
 
-        return BatchFeature(data={**text_inputs, **image_inputs}, tensor_type=return_tensors)
+        return BatchFeature(data={**text_inputs, **image_inputs, **videos_inputs}, tensor_type=return_tensors)
 
     def _expand_media_tokens(self, sample, media_token: str, media_iter: Iterable):
         media_count = sample.count(media_token)