My name is whybeyoung, and I work at an intelligent technology company in Hefei, with over 10 years of experience in the industry.
I specialize in cloud-native technologies, Kubernetes, OpenStack, Python, and large language models (LLMs).
I am also deeply involved in open-source communities, particularly around SGLang and AI infrastructure systems — passionate about bridging innovation and practicality in real-world AI workloads.
Feel free to reach out at [email protected] — I usually respond within an hour unless I'm deep in a cluster or lost in a new experiment.
This is my little corner of the cloud — a place where AI meets systems engineering.
Whether it’s optimizing PD-disaggregated inference, refining Kubernetes-based training platforms,
or exploring LLM performance on open infrastructures, I’m always chasing elegant, scalable solutions.
“In a world of distributed systems, even dreams should be parallelized.”