Woosuk Kwon

Woosuk Kwon is the co-founder and CTO of Inferact, an AI infrastructure company focusing on making LLM inference faster and cheaper.

Before founding Inferact, Woosuk was a PhD student at UC Berkeley’s Sky Computing Lab, where he co-created vLLM, one of the most widely used open-source inference engines. His research interests lie at the intersection of machine learning systems and large-scale infrastructure.

Appearances

• EP03: A User-Centric Perspective on LLM Inference

Key Contributions

• Co-creator of vLLM: Pioneered the use of PagedAttention for LLM serving.
• SkyPilot: Contributed to the development of SkyPilot, an inter-cloud broker for ML workloads.

Links

• Twitter / X
• Google Scholar
• GitHub