一作NeurIPS 2026Poster· Optimization / Neural Network Optimization
InQuant: In-Place Mixed-Precision KV Cache Quantization via Saliency-Aware Neighbor-Slot Reuse
Zihan Chang · Shuibing He · Bo Zhou · Ping Chen · Siling Yang
效率与系统OpenReview
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Zihan Chang · Shuibing He · Bo Zhou · Ping Chen · Siling Yang
Zihan Chang · Shuibing He · Bo Zhou · Sheng Xiao · Siling Yang · Rui Wang · Zhe Pan
In response to the increasing demand for largescale machine learning training jobs, many organizations have deployed GPU clusters across geographically distributed regions. However, existing ILP- or genetic-based cross-cluster training approaches largely overlook the topology of decentralized clu...