Li Zhuohan
Zhuohan Li is an AI research scientist at Meta who previously served as a member of technical staff at OpenAI, where he led infrastructure and inference work for gpt-oss and built systems for reasoning models. He co-created vLLM, the widely used open-source LLM serving engine, during his PhD studies at UC Berkeley under advisor Ion Stoica. He is best known for his contributions to efficient large language model inference infrastructure, including the PagedAttention technique.
“Zhuohan graduated early — in 2024. At that time if he started a company he'd be alone, because the other students were students, very inexpensive — just needed food, housing, a computer and internet to work.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.