issues
search
tspeterkim
/
flash-attention-minimal
Flash Attention in ~100 lines of CUDA (forward pass only)
Apache License 2.0
500
stars
40
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
expect implementation of flash attention-v2 and flash-decoding
#6
wisdom-miao
opened
1 month ago
0
Does this rep surport tensorcore?
#5
Rane2021
opened
2 months ago
2
Add matmul optimize
#4
Byeong-Chan
opened
3 months ago
0
slow in for loop test
#3
DefTruth
closed
3 months ago
2
Implement backward pass
#2
leloykun
opened
4 months ago
4
Correctness parameters
#1
cogumbreiro
closed
4 months ago
1