Recap: AI & Cloud Innovation Meetup Karlsruhe

Last week, we hosted the AI & Cloud Innovation Meetup at our Karlsruhe office, focusing on scaling Large Language Models from local to company-wide deployment. Our colleague Jonas Mayer discussed the necessary infrastructure for running various LLMs on custom hardware. As a member of our internal AI team, he shared insights from building a GPU cluster that hosts our in-house LLMs, making them accessible to our 900+ colleagues.

Thanks to everybody who joined us on-site. If you're interested in hosting your own LLMs and need guidance on setting up the infrastructure, don't hesitate to reach out. We're happy to help.