Zhiqiang Xie is a PhD candidate in computer science based in Palo Alto with nine years of engineering experience focused on building high-performance systems for AI model serving. He contributes to open-source infrastructure like SGLang, where he engineered hierarchical caching, a host memory pool, and a cache controller to improve memory management and latency for large language and vision models. Combining academic research with production-grade backend work, he excels at performance optimization and system-level refactors that make large models more practical to serve at scale. Known for a hands-on approach, he blends rigorous problem-solving from doctoral study with pragmatic engineering to deliver measurable efficiency gains.
SGLang is a fast serving framework for large language models and vision language models.
Role in this project:
Backend Engineer
Contributions:16 reviews, 27 PRs, 115 pushes in 1 year 2 months
Contributions summary:Zhiqiang primarily contributed to the development and optimization of the SGLang framework, focusing on memory management and caching strategies. They implemented a host memory pool for hierarchical caching and a cache controller, enhancing the system's efficiency. The user also introduced performance improvements and refactored components related to hierarchical caching, indicating a focus on optimizing large language model serving.
Contributions:140 commits, 52 pushes, 1 branch in 2 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.