SinkState: On-the-Fly SVD of Recurrent States for Efficient Hybrid LLM Serving

arXiv:2611.14246 · cs.LG · Submitted 2026-11-10 · Read on arXiv

cs.LG

Submitted: 2026-11-10

Updated: 2026-11-10

Code: https://github.com/fla-org/flash-linear-attention

Terminology

Sources

Related papers