this post was submitted on 22 Nov 2023
1 points (100.0% liked)

LocalLLaMA

3 readers
1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 1 year ago
MODERATORS
communick@poweruser.forum
1
Exponentially Faster Language Modelling: 40-78x Faster Feedforward for NLU thanks to FFFs (arxiv.org)
submitted 11 months ago by lexected@alien.top to c/localllama@poweruser.forum
4 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] edwios@alien.top 1 points 11 months ago

Misread title as “… thanks to F FFS” 😂 Joke aside, we should be seeing a 10-20x speed up for the current gen AI including text, sound and images. That would be a pivotal moment for gen AI.