Son Nguyen
|
478ee666cc
Make namespace comment consistent (#1305)
|
1 месяц назад |
jayhshah
|
c92ca63268
FA3 FP8 qkv descales + restore max offset for h128 causal + added sync for producer WG (#1173)
|
3 месяцев назад |
Tri Dao
|
bafe253042
[FA3] Bwd
|
4 месяцев назад |
jayhshah
|
5018ac6ac5
Fp8 kernel with "in-kernel" transpose of V in producer (#1100)
|
4 месяцев назад |
Tri Dao
|
7f67966cc7
FA3 initial code release
|
5 месяцев назад |