Kai Londenberg
|
b443207c1f
|
Paged Attention support for FA3 (#1268)
|
2024-11-09 17:05:01 -08:00 |
|
Son Nguyen
|
478ee666cc
|
Make namespace comment consistent (#1305)
Co-authored-by: Sony Nguyen <son.nguyen@bytedance.com>
|
2024-10-30 22:32:49 -07:00 |
|
jayhshah
|
a5a75274bc
|
FA3 kvcache + split kv + gqa parallelization (#1236)
|
2024-10-15 00:21:22 -07:00 |
|
Ying Zhang
|
dfe1a59e4b
|
Add var-seq-len to FA3 fp16 / bf16 fwd (#1072)
* fwd var-seq-len
* fixes
* benchmark
* fixes
---------
Co-authored-by: Tri Dao <tridao@users.noreply.github.com>
|
2024-07-22 21:32:41 -07:00 |
|