Google DeepMind just dropped this new LLM model architecture called Mixture-of-Recursions.
It gets 2x inference speed, reduced training FLOPs and ~50% reduced KV cache memory. Really interesting read.
Has potential to be a Transformers killer.
Iโm 23, starting an AI & robotics company. Founders: whatโs one brutal lesson you learned early on? Open to adviceโletโs connect!
#Startups