Woosuk Kwon
Source-listed: Co-founder and CTO · Inferact
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- vLLMSaved credit: Contributor · 2023Explore people connected to this work →
- Efficient Memory Management for Large Language Model Serving with PagedAttentionSaved credit: Contributor · 2023Explore people connected to this work →
- Jenga: Effective Memory Management for Serving LLM with HeterogeneitySaved credit: Contributor · 2025Explore people connected to this work →
- APEX: An Extensible and Dynamism-Aware Simulator for Automated Parallel Execution in LLM ServingSaved credit: Contributor · 2024Explore people connected to this work →
- TurboSpec: Closed-loop Speculation Control System for Optimizing LLM Serving GoodputSaved credit: Contributor · 2024Explore people connected to this work →