Cite
Notes
Only stored in your browser.
Attribution
APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs
arXiv 2025
from 1 papers
Chaojun Xiao
Hao Zhou
Jie zhou
Maosong Sun
professor
Sun Ao
Weilin Zhao
Xu Han
Yuxiang Huang
Zhiyuan Liu