5 papers
Characterize LSM-tree Compaction Performance via On-Device LLM Inference
Jiabiao Ding, Yina Lv, Qiao Li +2
Modern key-value storage engines built on Log-Structured Merge-trees (LSM-trees), such as RocksDB and LevelDB, rely heavily on the performance of their compaction operations, which…
Device-Level Optimization Techniques for Solid-State Drives: A Survey
Tianyu Ren, Yajuan Du, Jinhua Cui +3
Solid-state drives (SSDs) have revolutionized data storage with their high performance, energy efficiency, and reliability. However, as storage demands grow, SSDs face critical cha…
On-Demand Multi-Task Sparsity for Efficient Large-Model Deployment on Edge Devices
Lianming Huang, Haibo Hu, Qiao Li +2
Sparsity is essential for deploying large models on resource constrained edge platforms. However, optimizing sparsity patterns for individual tasks in isolation ignores the signifi…
GM-Skip: Metric-Guided Transformer Block Skipping for Efficient Vision-Language Models
Lianming Huang, Haibo Hu, Qiao Li +3
Transformer-based Vision-Language Models (VLMs) have achieved impressive performance on tasks such as image captioning, object recognition, and visual reasoning, but their high com…
Rethinking LSM-tree based Key-Value Stores: A Survey
Yina Lv, Qiao Li, Quanqing Xu +4
LSM-tree is a widely adopted data structure in modern key-value store systems that optimizes write performance in write-heavy applications by using append writes to achieve sequent…