Tri Dao
|
46fd2a20b2
|
Support all head dims that are multiples of 8, up to 128
|
2022-10-24 16:04:21 -07:00 |
|
Tri Dao
|
2ed471ecc4
|
Add tests for numerical error
|
2022-07-22 17:54:09 -04:00 |
|
Tri Dao
|
42f54d8840
|
Edit mention of Triton implementation
Phil Tillet suggests calling it "experimental".
|
2022-07-11 17:02:29 -07:00 |
|
Tri Dao
|
4577151ff8
|
Link to Triton implementation
|
2022-07-11 16:01:43 -07:00 |
|
Tri Dao
|
d1fc80a3bb
|
Link to IEEE Spectrum article on MLPerf
|
2022-07-10 12:11:46 -07:00 |
|
Tri Dao
|
1bbebccc0a
|
Edit README to mention bf16 support
|
2022-07-09 23:34:29 -07:00 |
|
Tri Dao
|
de19de7ab1
|
Implement for bf16
|
2022-07-09 23:31:56 -07:00 |
|
Tri Dao
|
6c3a8c65af
|
Implement cross attention
|
2022-07-03 17:48:12 -07:00 |
|
Tri Dao
|
450b64fe44
|
Add README section on issues
|
2022-06-27 13:50:16 -07:00 |
|
Dan Fu
|
765741c1ee
|
More explanation
|
2022-06-14 11:55:14 -07:00 |
|
Dan Fu
|
2d5b2483b8
|
Speedup graph for A100, d128
|
2022-06-14 11:54:16 -07:00 |
|
Tri Dao
|
d3e6440958
|
Implement bwd for head dim 128
|
2022-06-11 17:52:36 -07:00 |
|
Dan Fu
|
0a398dfc37
|
Broken link
|
2022-06-04 17:28:45 -07:00 |
|
Dan Fu
|
bd60750e0b
|
T4
|
2022-06-04 17:27:51 -07:00 |
|
Tri Dao
|
f2d8d4104e
|
Edit README: support Turing (SM75)
|
2022-06-04 16:06:48 -07:00 |
|
Dan Fu
|
ad6c694bb3
|
3090 speedup
|
2022-06-01 20:07:00 -07:00 |
|
Tri Dao
|
5a61cb7729
|
Rename src -> flash_attn
|
2022-06-01 18:50:26 -07:00 |
|
Tri Dao
|
c41479d66d
|
Support SM86 GPUs
|
2022-06-01 18:49:47 -07:00 |
|
Dan Fu
|
4b7cfb5f45
|
Citation
|
2022-05-30 13:29:04 -07:00 |
|
Tri Dao
|
a78745189a
|
Add paper arXiv link
|
2022-05-29 18:15:43 -07:00 |
|
Tri Dao
|
d9fff84bd0
|
Edit roadmap
|
2022-05-29 15:44:18 -07:00 |
|
Tri Dao
|
e4ffe5d50e
|
Convert banner figure from pdf to jpg
|
2022-05-29 15:39:17 -07:00 |
|
Tri Dao
|
67c3779598
|
Reorganize directories, add banner figure
|
2022-05-29 15:34:22 -07:00 |
|
Dan Fu
|
7025a092d1
|
Make png images into jpg for dark mode
|
2022-05-28 22:46:49 +01:00 |
|
Dan Fu
|
4decc3c166
|
README typo
|
2022-05-27 22:38:20 +01:00 |
|
Dan Fu
|
dc6d130088
|
Add speedup to README
Update images
Update images
Update description
|
2022-05-27 22:36:56 +01:00 |
|
Tri Dao
|
9dbc491aa5
|
Rename, add benchmarking script
|
2022-05-26 13:57:38 -07:00 |
|
Tri Dao
|
1fcbe6f0d0
|
First release
|
2022-05-20 14:21:58 -07:00 |
|