activity
20242026
collaborators

5 papers

cs.DB2026

O^3-LSM: Maximizing Disaggregated LSM Write Performance via Three-Layer Offloading

Qi Lin, Gangqi Huang, Te Guo +5

Log-Structured Merge-tree-based Key-Value Stores (LSM-KVS) have been optimized and redesigned for disaggregated storage via techniques such as compaction offloading to reduce the n…

cs.DC2025

TD-Orch: Efficient Task-Data Orchestration for Distributed Systems with Application to Graph Processing

Yiwei Zhao, Qiushi Lin, Hongbo Kang +5

We introduce a task-data orchestration abstraction that supports a range of distributed applications. Given a batch of lambda tasks each requesting a data item, where both tasks an…

cs.DB2025

StorageXTuner: An LLM Agent-Driven Automatic Tuning Framework for Heterogeneous Storage Systems

Qi Lin, Zhenyu Zhang, Viraj Thakkar +3

Automatically configuring storage systems is hard: parameter spaces are large and conditions vary across workloads, deployments, and versions. Heuristic and ML tuners are often sys…

cs.DB2025

ELMo-Tune-V2: LLM-Assisted Full-Cycle Auto-Tuning to Optimize LSM-Based Key-Value Stores

Viraj Thakkar, Qi Lin, Kenanya Keandra Adriel Prasetyo +4

Log-Structured Merge-tree-based Key-Value Store (LSM-KVS) is a foundational storage engine serving diverse modern workloads, systems, and applications. To suit varying use cases, L…

cs.LG2024

Split Knowledge Distillation for Large Models in IoT: Architecture, Challenges, and Solutions

Zuguang Li, Wen Wu, Shaohua Wu +3

Large models (LMs) have immense potential in Internet of Things (IoT) systems, enabling applications such as intelligent voice assistants, predictive maintenance, and healthcare mo…