12min chapter

The Data Exchange with Ben Lorica cover image

LLMs on CPUs, Period

The Data Exchange with Ben Lorica

CHAPTER

Utilizing CPU Resources for Faster and Cheaper Inference

This chapter explores the advantages of using CPUs over GPUs for certain tasks, such as increased hardware availability and control, potential cost savings, and the compatibility of their technology with different CPU providers. The speakers discuss the challenges and potential of offloading compute onto personal devices or a combination of both, emphasizing the abundance of untapped CPU resources in enterprise and cloud providers.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode