Poster · Sydney
Prism Attention: Proposal-Refined Index Sharing Mechanism for Efficient LLMs 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
- Zhenxu Tian, Kebin Liu, Zhengwu Yang, Yi Su, Qingqing Dang, Kaipeng Deng, Yanlin Sha, Yanjun Ma, Dianhai Yu, Juntao Li, Min zhang
- Organisations
- Soochow University, Baidu, Tencent, Harbin Institute of Technology
- QRS classification
- Attention and transformers, Language models