Talk alert! Compiling & Running SLMs on Edge

Our LLM and SLM wizard Thomas Ziereis joins the EDGE AI FOUNDATION's livestream on Generative Edge AI next week.

The rise of SLMs unlocks new possibilities for bringing powerful generative capabilities directly onto edge devices. However, compiling and executing SLMs present unique challenges that differ substantially from the traditional one-shot inference pipelines of other AI models.

Join the session to learn how roofline's compiler advancements can enable deployment for cutting-edge models on real hardware.

⏱️  Nov 17, 08:20AM PT / 05:20PM CET (updated slot)
📍 Register here: https://lnkd.in/enugDqa9
⚡ Can't make it or want to see a demo? Feel free to reach out!