SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training
Paper
•
2505.11594
•
Published
•
70
Jason Huang
jason-huang03
·
AI & ML interests
None yet
Recent Activity
authored
a paper
11 months ago
MoA: Mixture of Sparse Attention for Automatic Large Language Model
Compression
Organizations
