tests/pipelines/test_pipelines_text_generation.py · 305f41e4dea99d9fdc212287263b3748aacc63d3 · chenpangpang / transformers

Fix FP16 inference in TextGenerationPipeline (#20913) · fe65657d

bofeng huang authored Dec 29, 2022



* add torch_dtype attribute to Pipeline

* Use torch_dtype to cast input tensor type in AutomaticSpeechRecognitionPipeline

* Fix code quality

* Add TextGenerationPipeline fp16 test

* Fix code quality

* Remove useless require in tests
Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>

fe65657d

test_pipelines_text_generation.py 12.2 KB

Replace test_pipelines_text_generation.py