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_feature_extraction.py

@@ -174,7 +174,7 @@ class FeatureExtractionPipelineTests(unittest.TestCase):
             raise ValueError("We expect lists of floats, nothing else")
         return shape
 
-    def get_test_pipeline(self, model, tokenizer, processor):
+    def get_test_pipeline(self, model, tokenizer, processor, torch_dtype="float32"):
         if tokenizer is None:
             self.skipTest(reason="No tokenizer")
         elif (
@@ -193,7 +193,9 @@ class FeatureExtractionPipelineTests(unittest.TestCase):
                 For now ignore those.
                 """
             )
-        feature_extractor = FeatureExtractionPipeline(model=model, tokenizer=tokenizer, feature_extractor=processor)
+        feature_extractor = FeatureExtractionPipeline(
+            model=model, tokenizer=tokenizer, feature_extractor=processor, torch_dtype=torch_dtype
+        )
         return feature_extractor, ["This is a test", "This is another test"]
 
     def run_pipeline_test(self, feature_extractor, examples):