Systems researcherInfrastructure builder
Siyuan Zhuang
Co-built vLLM's PagedAttention, paging the KV cache like virtual memory to raise LLM serving throughput.
Works in the archive (1)
- PagedAttention / vLLM · 2023
“Lead” marks the first-listed author — a byline fact, not a measure of influence; co-authorship is shown as recorded.
Co-authors in the archive
View co-author network (5 people)
Loading graph…