10 papers
Why Does the LLM Stop Computing: An Empirical Study of User-Reported Failures in Open-Source LLMs
Guangba Yu, Zirui Wang, Yujie Huang +4
The democratization of open-source Large Language Models (LLMs) allows users to fine-tune and deploy models on local infrastructure but exposes them to a First Mile deployment land…
AI-NativeBench: An Open-Source White-Box Agentic Benchmark Suite for AI-Native Systems
Zirui Wang, Guangba Yu, Michael R. Lyu
The transition from Cloud-Native to AI-Native architectures is fundamentally reshaping software engineering, replacing deterministic microservices with probabilistic agentic servic…
Hierarchical Prediction-based Management for LMaaS Systems
Zhihan Jiang, Yujie Huang, Guangba Yu +3
Large Language Models (LLMs) have revolutionized numerous domains, driving the rise of Language-Model-as-a-Service (LMaaS) platforms that process millions of queries daily. These p…
Trace Sampling 2.0: Code Knowledge Enhanced Span-level Sampling for Distributed Tracing
Yulun Wu, Guangba Yu, Zhihan Jiang +2
Distributed tracing is an essential diagnostic tool in microservice systems, but the sheer volume of traces places a significant burden on backend storage. A common approach to mit…
Larger Is Not Always Better: Exploring Small Open-source Language Models in Logging Statement Generation
Renyi Zhong, Yichen Li, Guangba Yu +4
Developers use logging statements to create logs that document system behavior and aid in software maintenance. As such, high-quality logging is essential for effective maintenance…
CCISolver: End-to-End Detection and Repair of Method-Level Code-Comment Inconsistency
Renyi Zhong, Yintong Huo, Wenwei Gu +6
Comments within code serve as a crucial foundation for software documentation, facilitating developers to communicate and understand the code effectively. However, code-comment inc…