Woosuk Kwon
VERIFIED TECHNICAL DOSSIERSources checked

Woosuk Kwon

vLLM / UC Berkeley

2 Verified ArtifactsSource Checked & Attributed

Verified Proof of Work Artifacts

2 items cataloged

Each artifact below represents an authenticated research publication, production code repository, or technical architectural framework directly authored or co-created by Woosuk Kwon. Every entry undergoes editorial source verification.

#1
IMPLEMENTATION Checked 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.

Model & Execution Context:CUDA/ROCm kernels, Triton backends, Ray distributed orchestration, vLLM OpenAI-compatible server.
Scope & Limitations

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

#2
RESEARCH Checked 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.

Model & Execution Context:Evaluated across LLaMA, OPT, and Falcon architectures with continuous batching and multi-query attention.
Scope & Limitations

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