Haofeng Huang
- Papers
- 5
Cite
Notes
Only stored in your browser.
5papers
Authored papers
5XAttention: Block Sparse Attention with Antidiagonal Scoring
arXiv 2025
SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training
arXiv 2025
SageAttention2++: A More Efficient Implementation of SageAttention2
arXiv 2025
SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference
arXiv 2025
MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression
arXiv 2024
Affiliations
No known affiliations.
Frequent co-authors
10from 5 papers