david/flash-attention

peilaus alkaen https://github.com/Dao-AILab/flash-attention

Tekijä	SHA1 Viesti	Päivämäärä
Tri Dao	3f7d5786ba Pass alibi slopes to flash_attn_with_kvcache during generation	11 kuukautta sitten
Tri Dao	2c7d7b7396 Implement norm head for Baichuan2	1 vuosi sitten
Tri Dao	c3b2196652 Add Alibi to MHA, test with Baichuan-13B	1 vuosi sitten
GAOXinyu	a8c35b4f57 FEAT: add codes which supporting for baichuan-inc/Baichuan-7B (#425)	1 vuosi sitten