Cite
Notes
Only stored in your browser.
Attribution
CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMs
arXiv 2025
HyperAttention: Long-context Attention in Near-Linear Time
arXiv 2023
KDEformer: Accelerating Transformers via Kernel Density Estimation
from 3 papers
Amin Karbasi
Amir Zandieh
Chenliang Xu
David P. Woodruff
Haiting Lin
Jiani Liu
Kun Wan
Majid Daliri
Mingjie Zhao
Rajesh Jayaram