![[논문리뷰] Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://icml.cc/media/PosterPDFs/ICML%202024/32613.png)
[논문리뷰] Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
논문 링크 같은 논문을 2024-12-24 에도 한 번 더 정리해 두었다. Structured State Space Duality: Mamba-2로 본 SSM↔Attention 통일과 2–8× 가속한 줄 요약 (TL;DR)SSD(Structured …
44분
Mamba
SSM
Transformer
Long Context
Efficient Training
FlashAttention
GPU Acceleration