Poster "sub-quadratic complexity" Papers
2 papers found
Conference
A Training-Free Sub-quadratic Cost Transformer Model Serving Framework with Hierarchically Pruned Attention
Heejun Lee, Geon Park, Youngwan Lee et al.
ICLR 2025arXiv:2406.09827
9
citations
Fast attention mechanisms: a tale of parallelism
Jingwen Liu, Hantao Yu, Clayton Sanford et al.
NEURIPS 2025arXiv:2509.09001