4min chapter

Generally Intelligent cover image

Episode 33: Tri Dao, Stanford: On FlashAttention and sparsity, quantization, and efficient inference

Generally Intelligent

CHAPTER

The Future of Intuitive Learning

There are a couple of ways you can speed up inference. You can use sparsity where you're going to zero out some of the entries in the weight matrix. Instead of using 16 bits, you can use egg bits or four bits. These approaches are emerging and people are definitely paying attention. Maybe they're not kind of widely deployed yet but I think they will be in the future.

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