SpecLA: Efficient Speculative Decoding for Linear-Attention Models
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 existing speculative systems are designed for Transformer KV caches. For stateful linear-attention targets, verification must follow recurrent dependencies across chains and branches, acceptance must update only the accepted state trajectory, and the drafter must avoid submitting candidates that waste stateful verification work. This paper presents SpecLA, a speculative decoding runtime for stateful linear-attention models. SpecLA verifies chains and trees with topology-aware kernels, stores compact factors produced during verification to recover accepted states, and uses confidence pruning plus a target-aligned EAGLE-style drafter to feed useful candidates to the verifier. On an NVIDIA H100 with a public GDN-1.3B target, SpecLA achieves up to 1.70x end-to-end speedup over autoregressive decoding.
Cite
@article{arxiv.2607.16673,
title = {SpecLA: Efficient Speculative Decoding for Linear-Attention Models},
author = {Zhibin Wang and Xuying Han and Zhaohua Yang and Fuliang Liu and Xue Li and Rong Gu and Sheng Zhong and Chen Tian},
journal= {arXiv preprint arXiv:2607.16673},
year = {2026}
}