Allow FP16 or other precision inference for Pipelines (#31342)

* cast image features to model.dtype where needed to support FP16 or other precision in pipelines

* Update src/transformers/pipelines/image_feature_extraction.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Use .to instead

* Add FP16 pipeline support for zeroshot audio classification

* Remove unused torch imports

* Add docs on FP16 pipeline

* Remove unused import

* Add FP16 tests to pipeline mixin

* Add fp16 placeholder for mask_generation pipeline test

* Add FP16 tests for all pipelines

* Fix formatting

* Remove torch_dtype arg from is_pipeline_test_to_skip*

* Fix format

* trigger ci

---------

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

tests/pipelines/test_pipelines_zero_shot.py

@@ -42,9 +42,9 @@ class ZeroShotClassificationPipelineTests(unittest.TestCase):
             config: model for config, model in tf_model_mapping.items() if config.__name__ not in _TO_SKIP
         }
 
-    def get_test_pipeline(self, model, tokenizer, processor):
+    def get_test_pipeline(self, model, tokenizer, processor, torch_dtype="float32"):
         classifier = ZeroShotClassificationPipeline(
-            model=model, tokenizer=tokenizer, candidate_labels=["polics", "health"]
+            model=model, tokenizer=tokenizer, candidate_labels=["polics", "health"], torch_dtype=torch_dtype
         )
         return classifier, ["Who are you voting for in 2020?", "My stomach hurts."]