Dong-Yong Lee 8881f38a4f Fix beam search when using model parallel (#24969) ... * Fix GPTNeoX beam search when using parallelize * Fix beam search idx device when using model parallel * remove onnx related stuff Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com> * fix: move test_beam_search_on_multi_gpu to GenerationTesterMixin * fix: add right item to _no_split_modules of MegaPreTrainedModel * fix: add num_beams within parallelized beam_search test Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com> --------- Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com> Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>		2023-09-14 11:00:52 -04:00
..
adding_a_missing_tokenization_test	Move test model folders (#17034)	2022-05-03 14:42:02 +02:00
adding_a_new_example_script	Fix token in example template (#25351)	2023-08-08 12:00:31 +02:00
adding_a_new_model	Fix beam search when using model parallel (#24969)	2023-09-14 11:00:52 -04:00