Co-located Events ▼

Locations ▼

Text here

Request to partner

Luis

Ceze

CEO & Co-Founder

OctoML

Luis Ceze is Co-Founder and CEO of OctoML, which makes it easier to build AI powered apps through automated ML deployment. OctoML is backed by Tiger Global, Addition, Amplify Partners, and Madrona Venture Group. Ceze is the Lazowska Professor in the Paul G. Allen School of Computer Science and Engineering at the University of Washington, where he has taught for 15 years. He co-directs the Systems and Architectures for Machine Learning lab, which co-authored Apache TVM, a leading open-source ML stack for performance and portability that is used in widely deployed AI applications. He is also co-director of the Molecular Information Systems Lab (misl.bio), which led pioneering research in the intersection of computing and biology for IT applications such as DNA data storage. He is a Fellow of the ACM and his research has been featured prominently in the media including New York Times, Popular Science, MIT Technology Review, and the Wall Street Journal. Ceze is a Venture Partner at Madrona Venture Group and leads their technical advisory board.

19 October 2023 14:30 - 15:00

Run, tune, and scale generative models that power AI applications

Thanks to ChatGPT and Stable Diffusion, generative AI is no longer the domain of specialized engineers; it’s an essential part of any application developer’s toolkit. But getting a generative AI app to production is fraught with challenges: model selection, integration, price/performance optimization, monitoring, scale, and AI infrastructure management, just to name a few. App builders are trailblazing a new path because there is no clear GenAI playbook…yet. In this talk, Luis Ceze will share the easiest way to run, tune, and scale the models that power generative AI applications, including the latest open source and custom models, without having to become a machine learning or AI infrastructure expert. Luis will offer best practices and guidance for teams beginning their generative AI journey, as well as more advanced use cases for models like Llama2, SDXL, WhisperX and more.

Useful links

Summit series