 lancerts
|
22339db185
remove an unused import (#960)
|
il y a 7 mois |
 Tri Dao
|
ec6d22143b
[CrossEntropy] Change ignored_index -> ignore_index
|
il y a 8 mois |
 Curtis "Fjord" Hawthorne
|
d8aacc510c
return z_loss (#768)
|
il y a 11 mois |
|
Tri Dao
|
08124c8f9c
[CrossEntropy] Implement logit_scale option
|
il y a 1 an |
|
Tri Dao
|
aaa1474129
[CrossEntropy] Simplify the case of large vocab with Tensor Parallel
|
il y a 1 an |
 Shijie
|
abf04a56e1
fix flash ce mp large vocab (#673)
|
il y a 1 an |
|
Tri Dao
|
c79de85ffa
[CrossEntropy] Fix triton cross_entropy_loss IMA for >=2B elements
|
il y a 1 an |
|
Tri Dao
|
5400fdc4ac
[CE] Implement CrossEntropyLoss in Triton
|
il y a 1 an |
