5 papers
ElastiCo: Elastic Configuration and Interference-Aware Orchestration for GPU Clusters
Jinghao Wang, Yihang Zhou, Xiaoyang Sun +5
Modern GPU clusters must simultaneously serve deep learning training and offline large language model inference workloads, yet existing schedulers treat these as isolated resource…
SpecBox: Speculative Sandbox Scheduling for Efficient LLM Agent Serving
Yihui Zhang, Tianyu Wo, Jinghao Wang +7
As LLM agents increasingly rely on the Model Context Protocol (MCP) to invoke isolated external sandboxes, disaggregated sandbox deployment introduces a fundamental tension between…
RepoRescue: An Empirical Study of LLM Agents on Whole-Repository Compatibility Rescue
Zhihao Lin, Mingyi Zhou, Zhensu Sun +4
Open-source libraries and tools are widely reused, but compatibility maintenance is expensive. Once maintainers leave, useful repositories can stop working as runtimes and dependen…
To Run or Not to Run: Analyzing the Cost-Effectiveness of Code Execution in LLM-Based Program Repair
Zhihao Lin, Junhua Zhu, Mingyi Zhou +5
LLM-based agents for program repair are increasingly built on a "generate-run-revise" paradigm, iteratively executing tests to evaluate and refine patches. This execution-based app…
Distilling Cross-Modal Knowledge via Feature Disentanglement
Junhong Liu, Yuan Zhang, Tao Huang +2
Knowledge distillation (KD) has proven highly effective for compressing large models and enhancing the performance of smaller ones. However, its effectiveness diminishes in cross-m…