Tri Dao
|
b4bf9cc1f3
|
Fix performance regression with causal
|
2023-11-26 19:07:25 -08:00 |
|
Tri Dao
|
9e5e8bc91e
|
Change causal mask to be aligned to bottom-right instead of top-left
|
2023-08-24 23:41:07 -07:00 |
|
Tri Dao
|
4f285b3547
|
FlashAttention-2 release
|
2023-07-17 06:21:34 -07:00 |
|
Tri Dao
|
4360cfc6a8
|
[Triton] Fix benchmark_causal.py
|
2023-03-22 01:34:38 -07:00 |
|
Tri Dao
|
5d079fdd7a
|
[Triton] Fix benchmark_causal, mention Triton version
|
2023-03-22 00:51:16 -07:00 |
|
Tri Dao
|
b0c0db81f6
|
Implement FlashAttention in Triton
|
2022-10-30 18:09:11 -07:00 |
|
Tri Dao
|
ed553e9238
|
Add Megatron attention implementation for benchmarking
|
2022-10-23 23:04:16 -07:00 |
|
Tri Dao
|
50ca23488d
|
Add Triton implementation for benchmarking
|
2022-10-23 17:25:56 -07:00 |
|