Kai Londenberg
|
b443207c1f
Paged Attention support for FA3 (#1268)
|
1 mēnesi atpakaļ |
jayhshah
|
a5a75274bc
FA3 kvcache + split kv + gqa parallelization (#1236)
|
2 mēneši atpakaļ |
Ying Zhang
|
dfe1a59e4b
Add var-seq-len to FA3 fp16 / bf16 fwd (#1072)
|
4 mēneši atpakaļ |
Tri Dao
|
7f67966cc7
FA3 initial code release
|
5 mēneši atpakaļ |