Woosuk Kwon

vLLM / UC Berkeley

Sources checked
ABOUT

Co-creator and project lead of vLLM, and researcher at UC Berkeley SkyLab. Invented PagedAttention, a virtual memory paging algorithm for LLM key-value caches that eliminated memory fragmentation and increased LLM serving throughput by 2-4x across the AI industry.

Areas of focus

Professional niches

THE WORK BEHIND THE PROFILE

Proof of Work

implementationChecked Sep 21, 2026

vLLM: High-Throughput and Memory-Efficient LLM Serving Engine

Engineered and open-sourced vLLM, an enterprise serving system providing continuous batching, chunked prefill, speculative decoding, and tensor parallelism, serving billions of production inference tokens daily worldwide.

Scope & limitations

Requires dedicated GPU clusters and NVLink interconnects for multi-node tensor-parallel deployments.

Context: CUDA/ROCm kernels, Triton backends, Ray distributed orchestration, vLLM OpenAI-compatible server.

View mission
researchChecked Sep 21, 2026

Efficient Memory Management for Large Language Model Serving with PagedAttention

Authored the seminal SOSP 2023 paper introducing PagedAttention, inspired by operating system virtual memory paging, allowing non-contiguous KV-cache storage and near-zero memory waste during high-concurrency LLM inference.

Scope & limitations

Paged cache lookup introduces minor pointer indirection overhead in memory-bandwidth-bound token generation loops.

Context: Evaluated across LLaMA, OPT, and Falcon architectures with continuous batching and multi-query attention.

View mission

Guides to evaluating AI expertise