 Ying Zhang
|
496fdc4f6c
Add seqused_q in fwd / bwd and seqused_k in bwd.
|
4 сар өмнө |
 jayhshah
|
c92ca63268
FA3 FP8 qkv descales + restore max offset for h128 causal + added sync for producer WG (#1173)
|
4 сар өмнө |
|
Ying Zhang
|
53537da422
add a unittest
|
5 сар өмнө |
 Tri Dao
|
c33de664a1
Fix import in test
|
5 сар өмнө |
|
Tri Dao
|
bafe253042
[FA3] Bwd
|
5 сар өмнө |
|
jayhshah
|
5018ac6ac5
Fp8 kernel with "in-kernel" transpose of V in producer (#1100)
|
5 сар өмнө |
|
Tri Dao
|
3aae9c18c1
Revert "Changes For FP8 (#1075)"
|
6 сар өмнө |
 ganeshcolfax
|
1899c970c8
Changes For FP8 (#1075)
|
6 сар өмнө |
 Ying Zhang
|
dfe1a59e4b
Add var-seq-len to FA3 fp16 / bf16 fwd (#1072)
|
6 сар өмнө |
|
Tri Dao
|
74b0761ff7
[FA3] BF16 forward
|
6 сар өмнө |
|
Tri Dao
|
7f67966cc7
FA3 initial code release
|
6 сар өмнө |
