from Hacker News

Sparse Llama: 70% Smaller, 3x Faster, Full Accuracy

by panabee on 5/15/24, 11:36 PM with 1 comments

  • by free_bip on 5/16/24, 3:11 PM

    Specifically this is Llama2, not Llama3, was a bit disappointed from that. Also wasn't totally clear from the article - will this actually increase GPU inference speed / decrease GPU memory usage?