Unsupervised Learning cover image

Ep 74: Chief Scientist of Together.AI Tri Dao On The End of Nvidia's Dominance, Why Inference Costs Fell & The Next 10X in Speed

Unsupervised Learning

00:00

Evolving AI Inference Technologies

This chapter explores the advancements in inference technologies and the importance of tailored programming abstractions for GPU systems. It discusses the growing role of AI in generating GPU kernels, the significance of optimization techniques, and the balance between hardware capabilities and complex workloads. The conversation highlights innovative strategies, including Flash Attention and specialized architectures, that are driving significant performance improvements in AI applications.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app