Author name: Yu Zhang, Songwei Liu, Chenqian Yan, Sheng Lin, Beichen Ning, Fangmin Chen, Xing Wang

arXiv:2602.22575v2 Announce Type: replace
Abstract: Attention scales quadratically with sequence length, fundamentally limiting long-context inference. Existing block-granularity sparsification can reduce latency, but coarse blocks impose an intrinsic…