First vLLM Conference at Ray Summit

Hosted byInferact logo

August 25 - 26, San Francisco

The first vLLM Conference at Ray Summit brings together the engineers and researchers advancing open, high-performance inference.

Register here

Speaker lineup

Builders behind the vLLM ecosystem

Sessions cover the vLLM roadmap, hardware backends, training and serving integrations, and production-scale inference work.

Simon Mo profile photo
Inferact logo

Simon Mo

Cofounder / CEO, Inferact; Core Maintainer, vLLM

Woosuk Kwon profile photo
Inferact logo

Woosuk Kwon

Cofounder / CTO, Inferact; Creator / Core Maintainer, vLLM

Qi Zhou profile photo
Google TPU logo

Qi Zhou

Senior Staff Software Engineer, Google TPU

Siyuan Fu profile photo
NVIDIA logo

Siyuan Fu

Senior Engineer, NVIDIA

Debarshi Raha profile photo
DigitalOcean logo

Debarshi Raha

VP / Fellow Engineer, DigitalOcean

Greg Pereira profile photo
Red Hat logo

Greg Pereira

Sr. Machine Learning Engineer, Red Hat

Yifan Qiao profile photo
Inferact logo

Yifan Qiao

Member of Technical Staff, Inferact

Sami Jaghouar profile photo
Prime Intellect logo

Sami Jaghouar

Research Engineer, Prime Intellect

Zijing Liu profile photo
Inferact logo

Zijing Liu

Member of Technical Staff, Inferact

Jeffrey Wang profile photo
Anyscale logo

Jeffrey Wang

Software Engineer, Anyscale

Zachary Xi profile photo
Inferact logo

Zachary Xi

Product, Inferact

Sara Smoot profile photo
Google DeepMind logo

Sara Smoot

Software Engineering Manager, Google DeepMind / Gemma

Fred Wang profile photo
Together AI logo

Fred Wang

ML Research Engineer, Together AI / Lightseek

Ecosystem represented

Companies building around vLLM

Inferact logoNVIDIA logoGoogle TPU logoDigitalOcean logoRed Hat logoPrime Intellect logoAnyscale logoGoogle DeepMind logoGoogle Gemma logoTogether AI logoLightSeek logo