Inicio Explorar Axuda
Rexistro Iniciar sesión
david
/
flash-attention
réplica de https://github.com/Dao-AILab/flash-attention
1
0
Fork 0
Ficheiros Incidencias 0 Wiki
Rama: doc_masking
Ramas Etiquetas
flash-attention
/
flash_attn
/
modules
SueJane 3f1b4d38e7 Fix: check the type of max_seqlen_k instead of checking max_seqlen twice (#1127) hai 6 meses
..
__init__.py ece539abd6 Add __init__.py files to subdirectories for installation %!s(int64=2) %!d(string=hai) anos
block.py abbc131173 [LayerNorm] Switch from CUDA to Triton implementation hai 1 ano
embedding.py f1a73d0740 Run isort and black on python files hai 1 ano
mha.py 3f1b4d38e7 Fix: check the type of max_seqlen_k instead of checking max_seqlen twice (#1127) hai 6 meses
mlp.py c3b2196652 Add Alibi to MHA, test with Baichuan-13B hai 1 ano