Ideas & society2024 · shared on Hacker News
Mixture-of-Depths: Dynamically allocating compute in transformers
Explore Mixture-of-Depths: Dynamically allocating compute in transformers, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Ykolinko ·
Show HN: Speeding up LLM inference 2x times (possibly)
419 points114 comments
Ymilliondreams ·
Mixture-of-Depths: Dynamically allocating compute in transformers
281 points83 comments
YRafelMri ·
Antifragility in complex dynamical systems
173 points113 comments
YGaggiX ·
Mixture-of-Depths: Dynamically allocating compute in transformer language models
5 points2 comments
Ydekuma ·
Mixture-of-Depths: Dynamically allocating compute in transformers
4 points0 comments
Yalecco ·
DeepMind: Mixture-of-Depths: Dynamically allocating compute in transformers
2 points1 comments
YAnon84 ·
Dynamically allocating compute in transformer-based language models
2 points0 comments