Skip to content
NeurIPS 2026 planner

Poster · Sydney

InQuant: In-Place Mixed-Precision KV Cache Quantization via Saliency-Aware Neighbor-Slot Reuse

When
Tue 8 Dec 2026, 10:00–13:00 AEDT
Where
Hall 1-4, ICC Sydney
Exhibition Centre, Level 1
Session
Sydney Poster Session 1
Authors
Zihan Chang, Shuibing He, Bo Zhou, Ping Chen, Siling Yang
Organisations
Zhejiang University, Hangzhou High-Tech Zone Institute of Blockchain and Data Security
QRS classification
Language models, Efficient and distributed ML systems

Open in scheduleOfficial page