gewenbin0992 6a1ab634b6 qwen2.5vl: fix bugs when using flash2+bf16 or num_return_sequences>1 (#36083) ... * qwen2.5vl: fix bugs when using flash2+bf16 or num_return_sequences>1 * fix * fix * fix * fix * add tests * fix test bugs * fix * fix failed tests * fix		2025-02-13 11:35:28 +01:00
..
__init__.py	support qwen2-vl (#32318)	2024-08-26 15:16:44 +02:00
test_image_processing_qwen2_vl.py	use torch.testing.assertclose instead to get more details about error in cis (#35659)	2025-01-24 16:55:28 +01:00
test_modeling_qwen2_vl.py	qwen2.5vl: fix bugs when using flash2+bf16 or num_return_sequences>1 (#36083)	2025-02-13 11:35:28 +01:00
test_processor_qwen2_vl.py	Chat template: update for processor (#35953)	2025-02-10 09:52:19 +01:00