ReaDy: Recurrent States as Dynamic Context for Speculative Drafting in Hybrid Linear Attention Large Language Models
This work introduces ReaDy, the first speculative decoding method, to leverage HLA recurrent states for position-specific context retrieval during drafting, and achieves an average $3.16\times decoding speedup over autoregressive decoding with Qwen3.
Bo Sun, Zun-Hai Su, Xia-Lie Zhuang et al.
· 0 citations