Skip to content
NeurIPS 2026 planner

Poster · Sydney

BMAttn: Block-Aligned Mixed-Precision Attention Quantization for LLM Inference

When
Thu 10 Dec 2026, 17:00–20:00 AEDT
Where
Hall 1-4, ICC Sydney
Exhibition Centre, Level 1
Session
Sydney Poster Session 6
Authors
Zining Wang, Haojie Duanmu, Zhihang Yuan, Fanliu Kong, Ruihao Gong, Jinyang Guo, Xianglong Liu
Organisations
Shanghai Jiao Tong University, Peking University, Tsinghua University, ByteDance, SenseTime, Beihang University
QRS classification
Attention and transformers, Language models, Efficient and distributed ML systems

Open in scheduleOfficial page