The benefits of caching are that we can run the forward pass up to this final MLP without having done any changes to that early attention head. We do not edit the effect that in the example the early attention head has on all the middle components. It's a matter of caching those two like saving them as in your like Python code just nothing or complicated than that so that then once we're at the downstream node then we can do the editing.

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