david/flash-attention

огледало од https://github.com/Dao-AILab/flash-attention

Аутор	SHA1 Порука	Датум
Tri Dao	a93359a2bf If PackGQA, use producer threads instead of Mma threads to load Q	пре 1 месец
Tri Dao	7bc3f031a4 Compile for both Sm80 and Sm90	пре 1 месец
Tri Dao	7a802796e1 Big refactor and update	пре 1 месец