 jayhshah
|
a5a75274bc
FA3 kvcache + split kv + gqa parallelization (#1236)
|
há 3 meses atrás |
 hlky
|
8476986721
Fix FAv3 compilation with MSVC (#1240)
|
há 4 meses atrás |
 Ying Zhang
|
dff976a84a
fixes
|
há 4 meses atrás |
 Tri Dao
|
bafe253042
[FA3] Bwd
|
há 5 meses atrás |
|
jayhshah
|
5018ac6ac5
Fp8 kernel with "in-kernel" transpose of V in producer (#1100)
|
há 5 meses atrás |
|
Tri Dao
|
3aae9c18c1
Revert "Changes For FP8 (#1075)"
|
há 6 meses atrás |
 ganeshcolfax
|
1899c970c8
Changes For FP8 (#1075)
|
há 6 meses atrás |
 janEbert
|
3c4053b75c
Make FA3 externally importable (#1053)
|
há 6 meses atrás |
|
Tri Dao
|
74b0761ff7
[FA3] BF16 forward
|
há 6 meses atrás |
|
Tri Dao
|
7f67966cc7
FA3 initial code release
|
há 6 meses atrás |
