It is found that the speculative-decoding module in recent LLMs can be repurposed for efficient high-quality classification by appending a trained soft prompt at the end of the target sequence, which can repurpose the speculative-decoding module into a sequence classifier.
Abstract
Real-time classification during language model inference is valuable for safety filtering, behavioral analysis, and model monitoring, but current approaches force a trade-off between accuracy and efficiency. Hidden-state probes are fast but limited: they are either not context-aware: operating on a single vector and cannot model interactions across positions; or they are very costly: having dedicated classifier models (Llama Guard, Qwen Guard, LLM-as-judge) or performing computation on hidden states for all tokens and then pooling the results (MultiMax). This shows an intrinsic trade-off between efficiency and accuracy. However, we find that the speculative-decoding module in recent LLMs can be repurposed for efficient high-quality classification. By appending a trained soft prompt at the end of the target sequence, we can repurpose the speculative-decoding module into a sequence classifier. At inference time in a speculative-decoding pipeline, the KV cache is already in GPU memory, so classification adds negligible overhead. We evaluate on four classification tasks across four models (Qwen3.5-4B, 9B, 27B, MiniCPM4.1-8B). Our small probes consistently outperform zero-shot GPT-5.4-mini and, on multilingual prompt safety, match or beat specialized 8B safety classifiers (Qwen3Guard-Gen-8B, Llama-Guard-3-8B) without running a full LLM.
Five self-speculative decoding techniques are characterized across three model sizes and three datasets and recommendations for future research in this area are provided.
Jungmin Ha, Karthik Ganesan, Anh Nguyen et al.· 0 citations
DFly is proposed, a block-diffusion framework combining a hybrid target-conditioning backbone with a predecessor-conditioned autoregressive head, improving target-feature utilization and intra-block dependency modeling while keeping generation parallel, and DFly treats verification as a shared batch-level resource.
A unified efficiency analysis is presented showing that extending the speculation horizon can reduce rather than improve speedup when the marginal acceptance probability falls below the relative drafting cost, and SparseSpec-L, a training-free self-speculative decoding framework for long-context inference is introduced.
Single-stream autoregressive decoding of large language models is bound by memory bandwidth: each generated token requires one full forward pass through the target model, and successive passes cannot be parallelized. Speculative decoding restructures this computation: a small draft model proposes $K$ tokens autoregressively, the target model scores all of them in one batched pass, and a rejection-sampling rule provably preserves the target model's output distribution. We present a from-scratch, device-agnostic (CUDA/MPS/CPU) implementation and an empirical study across five draft/target backend configurations on a consumer Apple-silicon laptop. Distribution equivalence is verified at three levels, culminating in a two-sample test over roughly 9,200 real-model tokens per method ($\chi^2 = 162.5$, dof $= 200$, $p = 0.976$) and exact greedy-sequence agreement. The best configuration reaches a measured $1.61\times$ wall-clock speedup at $K=6$, on an acceptance profile declining from 69.7% at $K=1$ to 37.8% at the optimum, while three of five configurations decelerate, either because the draft fails to out-speed a small target or because the quantized Metal backend executes"parallel"verification serially, an effect we isolate and quantify. The failures are as instructive as the successes: speculative decoding pays off only when verification is genuinely batch-parallel and the draft/target latency gap is real.
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.
Zhibin Wang, Xuying Han, Zhaohua Yang et al.· 0 citations
Speculative Decoding (SD) accelerates large language model inference by allowing a lightweight draft model to propose tokens that are subsequently verified in parallel by a larger target model. Recent approaches introduce lossy verification schemes to further improve efficiency by relaxing strict distributional matching. Yet such relaxation silently rewrites the decoding distribution, and the resulting acceleration can come at the cost of unstable, sometimes severely degraded generation quality. In this work, we present a principled analysis of the distributions induced by lossy verification methods. We show that many seemingly distinct approaches differ only superficially and can be classified into two categories: truncation-based verification and collaborative verification. We further construct a diagnostic evaluation framework across curated benchmarks. For truncation-based methods, we identify a fundamental pitfall: performance can degrade significantly compared to the true truncation sampling baseline due to distributional distortion. For collaborative verification, we uncover a key principles: controlling the overshoot of draft probabilities relative to target probabilities is essential to prevent low-quality outputs. Our code is available at https://github.com/ZhouYuxuanYX/Fast-HSD.
Tianyu Wang, Yuxuan Zhou, Wenbin Wang et al.· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduAug 31, 2026
With millions of users across the world, Julia has been used to conduct cutting-edge research and to design new drugs, jet engines, heat pumps, and more.
