Startseite Erkunden Hilfe
Registrieren Anmelden
david
/
flash-attention
Mirror von https://github.com/Dao-AILab/flash-attention
1
0
Fork 0
Dateien Issues 0 Wiki
Branch: ipiszy/local_attn
Branches Tags
flash-attention
/
csrc
rocking e2182cc21d Support page kvcache in AMD ROCm (#1198) vor 6 Monaten
..
composable_kernel @ a9b170b541 e2182cc21d Support page kvcache in AMD ROCm (#1198) vor 6 Monaten
cutlass @ 756c351b49 74b0761ff7 [FA3] BF16 forward vor 8 Monaten
flash_attn 65f723bb9a Split bwd into more .cu files to speed up compilation vor 8 Monaten
flash_attn_ck e2182cc21d Support page kvcache in AMD ROCm (#1198) vor 6 Monaten
ft_attention 50896ec574 Make nvcc threads configurable via environment variable (#885) vor 1 Jahr
fused_dense_lib 50896ec574 Make nvcc threads configurable via environment variable (#885) vor 1 Jahr
fused_softmax 50896ec574 Make nvcc threads configurable via environment variable (#885) vor 1 Jahr
layer_norm 50896ec574 Make nvcc threads configurable via environment variable (#885) vor 1 Jahr
rotary 50896ec574 Make nvcc threads configurable via environment variable (#885) vor 1 Jahr
xentropy 50896ec574 Make nvcc threads configurable via environment variable (#885) vor 1 Jahr