4 papers
Janus: Disaggregating Attention and Experts for Scalable MoE Inference
Zhexiang Zhang, Ye Wang, Yumiao Zhao +10
Serving large Mixture-of-Experts (MoE) models is challenging because of their large memory footprints, heterogeneous resource demands, and highly dynamic inference workloads. Most…
ConZone+: Practical Zoned Flash Storage Emulation for Consumer Devices
Dingcui Yu, Zonghuan Yan, Jialin Liu +5
To facilitate the understanding and efficient enhancement of software and hardware design for consumer-grade zoned flash storage, ConZone is proposed as the first emulator designed…
Waltz: Temperature-Aware Cooperative Compression for High-Performance Compression-Based CSDs
Dingcui Yu, Yunpeng Song, Yiyang Huang +5
Data compression is widely adopted for modern solid-state drives (SSDs) to mitigate both storage capacity and SSD lifetime issues. Researchers have proposed compression schemes at…
RARO: Reliability-aware Conversion with Enhanced Read Performance for QLC SSDs
Yanyun Wang, Dingcui Yu, Yina Lv +3
Quad-level cell (QLC) flash offers significant benefits in cost and capacity, but its limited reliability leads to frequent read retries, which severely degrade read performance. A…