Kalman Delta Networks: Uncertainty-aware Associative Memory
Linear Attention Rewritten with a Kalman Filter: Kalman Delta NetworksTL;DRThe fixed-size recurrent memory update of linear attention is …
16 min
KV Cache
Long Context
Efficient Inference
SSM
Attention Optimization
Kalman Filter
![[Paper Review] Marconi: Prefix Caching for the Era of Hybrid LLMs](https://pbs.twimg.com/media/GdyLXO9W4AADox0.jpg)
![[Paper Review] Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://icml.cc/media/PosterPDFs/ICML%202024/32613.png)