Skip to content

Why You Can't Just Rent 1,000 GPUs | Charles Frye (Modal)

About

Charles Frye of Modal examines the infrastructure constraints behind large-scale AI research. With Ravid Shwartz Ziv and Allen Roush, he discusses underused hardware, saturated resources, sharing GPU capacity and deciding when to train a model. The conversation also covers inference and speculative decoding, hardware economics, virtualization and the security boundaries around agents and open models. Hosted by Ravid Shwartz Ziv and Allen Roush. Watch the full conversation on the publisher’s YouTube channel.

Topics

large-scale AI researchunderused hardwareGPU capacityinferencespeculative decodinghardware economicsvirtualizationopen models

More from this series

More from The Information Bottleneck

All episodes

More with Ravid Shwartz Ziv

All their work

More with Allen Roush

All their work

New episodes in Computer Science

All episodes

We use cookies for analytics.