Guangtao Xue

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...

Cloud local storage has been a popular service among many vendors thanks to its near-physical performance and affordable price. In this paper, we revisit the evolution of the cloud local storage at Alibaba Cloud. We systematically analyze and evaluate the motivations, architectures and pros/cons...

Large Language Models (LLMs) are increasingly deployed in agent-based applications with complex prompt structures comprising both invariant and dynamic segments. Existing KV cache reuse strategies—PositionDependent Caching (PDC) and Position-Independent Caching (PIC)—inadequately address these s...

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...

File synchronization (sync) is of increasing significance for not only intra-cloud but also inter-cloud applications and services, as cloud computing is evolving into the Sky computing paradigm with the illusion of utility computing on an infrastructure of multiple geographically-distributed clou...

File synchronization (sync) based on Content-Defined Chunking (CDC) is gaining increasing importance for data migration over networks owing to its effectiveness in detecting and eliminating duplicate data within synchronized files. CDC-based sync schemes typically comprise three phases: file chun...