Haonan Wu

Large Language Model (LLM) inference services in production operate under stringent, fine-grained Service Level Objectives (SLOs). Unlike throughput-oriented LLM training, even sporadic performance anomalies during inference can violate SLOs, underscoring the need for improved tracing and diagnos...

Efficient cloud computing relies on high-performance Elastic Block Storage (EBS) services, where virtual disk (VD) image loading significantly affects user experience. While the commonly used "lazy loading" approach reduces cold-start time from minutes to sub-seconds, our trace analysis of around...