Systems researcherInfrastructure builder
Ion Stoica
Co-led vLLM and PagedAttention, raising LLM serving throughput through paged KV-cache memory management.
Works in the archive (3)
- PagedAttention / vLLM · 2023
- Edge/Format Ecosystem (llama.cpp/GGUF/TensorRT-LLM/SGLang) · 2023
- Chatbot Arena / LLM-as-Judge (MT-Bench/AlpacaEval) · 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 (11 people)
Loading graph…