HomeAI & MLAwesome NLP › Characterizing SSM and Hybrid LM Long-Context Performance

Characterizing SSM and Hybrid LM Long-Context Performance

arxiv.org ↗

(2025) - first comprehensive memory and speed analysis of transformer, SSM, and hybrid models up to 220K tokens; SSMs are up to 4x faster, hybrids balance recall and efficiency.

↵ to searchesc to close
awesomelist.dev