Tri Dao
|
e45a46a5b7
[Rotary] Implement GPT-J style (interleaved) rotary
|
hai 1 ano |
Tri Dao
|
1e712ea8b0
Implement TensorParallel for MHA
|
%!s(int64=2) %!d(string=hai) anos |
Tri Dao
|
ca81f32e04
Implement rotary embedding in CUDA
|
%!s(int64=2) %!d(string=hai) anos |