 Tri Dao
|
6e8b25e426
Refactor
|
2 ماه پیش |
 Ying Zhang
|
7b4e68e04f
hopper local attention
|
3 ماه پیش |
|
Ying Zhang
|
db80387343
Add seqused_q in fwd / bwd and seqused_k in bwd.
|
3 ماه پیش |
 jayhshah
|
c92ca63268
FA3 FP8 qkv descales + restore max offset for h128 causal + added sync for producer WG (#1173)
|
3 ماه پیش |
|
Tri Dao
|
bafe253042
[FA3] Bwd
|
4 ماه پیش |
 Ying Zhang
|
dfe1a59e4b
Add var-seq-len to FA3 fp16 / bf16 fwd (#1072)
|
4 ماه پیش |
 Cameron Shinn
|
cb516f855b
Remove torchlib dependency from cpp files (#1083)
|
4 ماه پیش |
|
Tri Dao
|
74b0761ff7
[FA3] BF16 forward
|
5 ماه پیش |
|
Tri Dao
|
7f67966cc7
FA3 initial code release
|
5 ماه پیش |
