1028: The Chip Built for Agentic AI Inference, with SambaNova's Anton McGonnell

GPUs are today, of course, the workhorse of AI inference in production, but they aren't actually optimized for that. My guest today is Anton McGonnell, VP of product at SambaNova, a Bay Area company that has raised over $2 billion to develop a chip optimized for AI inference.

It goes beyond the title with direct discussion of inference, really, data, including: Today's guest built a new chip that is pushing the frontier of real-time AI speed and bandwidth.

1. 01GPUs are today, of course, the workhorse of AI inference in production, but they aren't actually optimized for that
2. 02My guest today is Anton McGonnell, VP of product at SambaNova, a Bay Area company that has raised over $2 billion to develop a chip optimized for AI inference
3. 03In this episode, Anton explains why Agentic AI has changed the shape of inference workloads and how SambaNova's chip sidesteps the memory bottleneck that slows GPUs when generating