Deepseek v4 csa mask collapse #45928
ArthurZucker
force pushed
from
eacc6a1c
to
65483d8c
159 days ago
ArthurZucker
force pushed
from
65483d8c
to
572de4ec
159 days ago
ArthurZucker
marked this pull request as ready for review 159 days ago
[deepseek_v4] collapse CSA block_bias from [S, S*top_k] to [S, compreā¦
bd900875
ArthurZucker
force pushed
from
572de4ec
to
bd900875
159 days ago
ArthurZucker
deleted the deepseek-v4-csa-mask-collapse branch 159 days ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub