SageAttention2 Technical Report: Accurate 4 Bit Attention for Plug-and-play Inference Acceleration
Paper
•
2411.10958
•
Published
•
47
•
6
kaideng
dk666
AI & ML interests
None yet
Recent Activity
commented
a paper
7 days ago
SageAttention2 Technical Report: Accurate 4 Bit Attention for
Plug-and-play Inference Acceleration
Organizations
dk666's activity
commented
a
paper
7 days ago