home.social

#mechanisms — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #mechanisms, aggregated by home.social.

  1. Build DeepSeek-V3: Multi-Head Latent Attention (MLA) Architecture Table of Contents Build DeepSeek-V3: Multi-Head Latent Attention (MLA) Architecture The KV Cache Memory Problem in DeepSeek-V3 Mult...

    #Deep #Learning #Large #Language #Models #PyTorch #Transformers #Tutorial #attention #mechanisms #deepseek-v3

    Origin | Interest | Match
  2. How petrol pumps know when to turn themselves off

    youtube.com/watch?v=fT2KhJ8W-Kg

    Some of these everyday things in our life are in extremely clever ways that simply how it works can blow your mind. This is an example of that, and it all of the involved in such a simple and intuitive way that anyone could understand it. Definitely one of the best I've seen.