Skip to content
arXiv cs.CL · Papers

SpecLA: Efficient Speculative Decoding for Linear-Attention Models

arXiv:2607.16673v1 Announce Type: new Abstract: Linear-attention models replace the growing KV cache with recurrent states, but autoregressive decoding still reads, updates, and writes these states one token at a time. Speculative decoding can reduce this cost by verifying several draft tokens in one target pass, yet e