 Tri Dao
|
7bc3f031a4
Compile for both Sm80 and Sm90
|
hace 2 semanas |
|
Tri Dao
|
7a802796e1
Big refactor and update
|
hace 2 semanas |
 Ying Zhang
|
1c9717d699
address comments
|
hace 4 meses |
|
Ying Zhang
|
dff976a84a
fixes
|
hace 4 meses |
|
Ying Zhang
|
7b4e68e04f
hopper local attention
|
hace 4 meses |
|
Ying Zhang
|
db80387343
Add seqused_q in fwd / bwd and seqused_k in bwd.
|
hace 5 meses |
 Cameron Shinn
|
3cea2fb6ee
Add ArchTag to pre/postprocess bwd kernels (#1180)
|
hace 5 meses |
|
Tri Dao
|
bafe253042
[FA3] Bwd
|
hace 5 meses |
|
Cameron Shinn
|
cb516f855b
Remove torchlib dependency from cpp files (#1083)
|
hace 6 meses |
|
Tri Dao
|
7f67966cc7
FA3 initial code release
|
hace 6 meses |
