# SpecLA: Efficient Speculative Decoding for Linear-Attention Models

arXiv: https://arxiv.org/abs/2607.16673 · HTML: https://mlsanity.com/paper/2607.16673/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Speculative decoding, one of 12 directions in Efficient LLM inference and serving.
- Builds on 10 of its 27 references that are in the map.
- First posted on arXiv 18 Jul 2026.

## Placed in

- Efficient LLM inference and serving / [Speculative decoding](https://mlsanity.com/inference/speculative-decoding/)

## Builds on (most cited first, 10 of 10)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [Gated Delta Networks: Improving Mamba2 with Delta Rule](https://mlsanity.com/paper/2412.06464/) (2024)
- [EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees](https://mlsanity.com/paper/2406.16858/) (2024)
- [EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test](https://mlsanity.com/paper/2503.01840/) (2025)
- [Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding](https://mlsanity.com/paper/2402.05109/) (2024)
- [Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels](https://mlsanity.com/paper/2503.14376/) (2025)
- [STree: Speculative Tree Decoding for Hybrid State-Space Models](https://mlsanity.com/paper/2505.14969/) (2025)
- [A Persistent-State Dataflow Accelerator for Memory-Bound Linear Attention Decode on FPGA](https://mlsanity.com/paper/2603.05931/) (2026)

## Built on by (most cited first, 4 of 4)

- [Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training](https://mlsanity.com/paper/2609.07108/) (2026)
- [LumoTree: Path-Parallel Speculative Verification for Hybrid Language Models](https://mlsanity.com/paper/2609.23900/) (2026)
- [CAST: Cost-Aware Speculative Trees from One-Pass Block Drafters](https://mlsanity.com/paper/2610.00321/) (2026)
- [ReaDy: Recurrent States as Dynamic Context for Speculative Drafting in Hybrid Linear Attention Large Language Models](https://mlsanity.com/paper/2610.20503/) (2026)

## Abstract (arXiv)

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.