 Tri Dao
|
d5893f3c74
Merge branch 'main' into changes_for_fp8
|
vor 4 Monaten |
 Ying Zhang
|
dfe1a59e4b
Add var-seq-len to FA3 fp16 / bf16 fwd (#1072)
|
vor 4 Monaten |
 Ganesh Bikshandi
|
df66e974bc
fixed odd-seq-len-k.
|
vor 4 Monaten |
|
Ganesh Bikshandi
|
4eacd5886d
enable all tests except odd-seq-lengths, where it crashes now.
|
vor 4 Monaten |
|
Ganesh Bikshandi
|
d5c2d1aa18
removed contiguous check.
|
vor 4 Monaten |
|
Ganesh Bikshandi
|
cdc966e81a
adding files for fp8 changes.
|
vor 4 Monaten |
 Tri Dao
|
74b0761ff7
[FA3] BF16 forward
|
vor 5 Monaten |
|
Tri Dao
|
7f67966cc7
FA3 initial code release
|
vor 5 Monaten |
