user avatar
Flash-Attn: fix generation when no attention mask or no pading (#32241)
Raushan Turganbay authored
* fix

* fix prev test (half of failures)

* [run-slow] llama, gemma2

* [run-slow] llama, gemma2
81233c06
Forked from zhusg / transformers-new
Source project has a limited visibility.
Name Last commit Last update