Speculative Decoding

Follow this topic Ask about this topic

Speculative decoding aims to reduce the time and computation needed to generate text by letting a drafter propose future tokens for a target model to check. Approaches include small auxiliary drafters, early-exit or multi-token prediction within the target model, and tree-based or block-parallel drafting; retrieval and task-specific signals can also supply candidates. Exact verification can preserve the target model’s output distribution, while relaxed acceptance rules trade some fidelity for speed. A central challenge is making gains in accepted tokens translate into real latency or throughput improvements across different workloads, hardware, and serving loads.

Latest papers

309 papers74 papers in the last four weeks, up 118% on the four weeks before. 0.4% of all new papers.

Sep 18, 2026

Watermarkable Multi-Draft Speculative Sampling via Poisson Processes

Large language models (LLMs) have achieved state-of-the-art performance across a wide range of tasks, motivating two important aspects of deployment: inference efficiency and output provenance, which can be tackled by speculative sampling and watermarking, respectively. However, recent works have shown that combining these two goals is highly nontrivial and can be potentially impossible. In this work, we develop a novel multi-draft speculative sampling algorithm based on Poisson processes that improves the frontier of this fundamental trade-off. The proposed algorithm has strong sampling efficiency on its own and, more interestingly, is naturally watermarkable: we can embed an unbiased watermark without degrading speculative acceptance. Moreover, our algorithm is based on an exact list-coupling-without-communication scheme, which yields a drafter invariance property that benefits both sampling and watermarking. It is the first multi-draft, drafter-invariant speculative sampling scheme that maintains both watermark strength and sampling efficiency, and we experimentally verify its strong performance in both aspects.

Yanxiao Liu, Sicheng Wan, Zhan Gao +1

Imperial College London · University of Washington

Speculative Decoding LLM Inference Acceleration LLM Watermarking

Sep 18, 2026

RheoSampling: Resolving the One-Hot Dilemma in Stochastic Dynamic-Tree Speculative Decoding

Speculative decoding accelerates LLM inference by drafting multiple tokens in parallel, with tree-based methods further improving efficiency through hierarchical structures. Dynamic-tree methods such as EAGLE-3 perform well under greedy decoding via deterministic top-K expansion and global pruning. However, in stochastic decoding (T>0), this mechanism collapses the draft distribution into one-hot probabilities, causing a severe drop in acceptance rate. This creates a dilemma: dynamic-tree methods sacrifice stochastic sampling to preserve context-aware topology, while static-tree methods preserve stochastic sampling with context-agnostic structures. The issue arises because the same probability distribution is used for two conflicting tasks: constructing the tree and verifying tokens. This coupling makes direct injection of randomness challenging due to the resulting stochastic process. We resolve this by decoupling these roles: RheoSampling assigns a token sampled from the draft distribution a proxy probability for tree expansion and pruning alongside its true sampling probability for verification. Specifically, we inject a sampled token among the deterministic top-K slots and treat it with different probabilities during construction and verification, making RheoSampling the first dynamic-tree method with both context-aware top-K construction and stochastic sampling while maintaining losslessness. We establish the lossless guarantee through an equivalence-class analysis that compresses the stochastic tree space into tractable classes. An OT-based verification strategy and a sparse draft mechanism ensure that theoretical gains translate into practical efficiency. Experiments across LLMs and benchmarks demonstrate improvements in acceptance rate and speedup over state-of-the-art dynamic tree methods. This framework may provide a template for analyzing stochastic tree structures.

Qiao Hu, Yepeng Weng, Bo Zhang +1

National Center for Mathematics and Interdisciplinary Sciences (NCMIS), AMSS, CAS · The University of Tokyo · Lenovo AI Technology Center +2

Speculative Decoding LLM Inference Acceleration

Sep 18, 2026

SpecQuant: Speculative Decoding with Multi-Parent Quantization for Adaptive LLM Inference

Running large language models (LLMs) locally continues to be limited by restrictions of compute and memory on consumer hardware. The popular acceleration technologies, such as quantization, speculative decoding, and adaptive inferencing, offer substantial speed boosts but usually necessitate retraining, per architecture tuning, or draft models. SpecQuant is a trainingfree framework, that combines speculative decoding with multiparent quantization to perform adaptive, efficient inference of LLMs. SpecQuant derives multiple quantized variants (INT4, FP8, FP16) from a shared base model, and dynamically routes queries based on predicted complexity; lightweight variants are used for simple or factual tasks, and full-precision models are used for complex reasoning tasks or long-context inputs. The shared-weight design of SpecQuant ensures sufficient token acceptance for speculative decoding without compatibility issues using separate draft parent models. We evaluate SpecQuant on Qwen2.5 based models on the MMLU, AlpacaEval, and GSM8K datasets, or benchmarks, demonstrating 35-43% speedups without degrading accuracy greater than 2%, substantial within the LLM community. SpecQuant enables practical on-device LLM deployment across diverse hardware without special infrastructure or expertise.

Harish KB, Jagadeeswaran M, Pradheep P +2

Computer Science and Engineering Vellore Institute of Technology Vellore, India

LLM Inference LLM Inference Acceleration On-Device Language Model Inference LLM Quantization Speculative Decoding

Sep 17, 2026

To Copy or Not to Copy: Controlling Speculative Decoding via Intrinsic Model Signals

Speculative Decoding (SD) has significantly accelerated Large Language Model (LLM) inference, yet existing approaches face a fundamental tradeoff between two drafting strategies: neural drafting and context-based copying. Neural drafts (e.g., EAGLE3) provide robust performance across diverse text settings, while copy-based methods achieve higher speedups in copy-intensive regimes by generating candidates faster and exploiting long repetition spans for near-perfect speculation. We analyze existing copy-based methods and find that they are prone to accidental repetitions where surface-level n-gram overlap does not reflect a structural intent to copy, leading to false-positive triggers that ultimately degrade throughput. We introduce SwitchSD, an adaptive framework that treats copying as a latent control signal of the LLM. By training lightweight probes on the target model's internal representations, SwitchSD identifies genuine copy-intent with high precision (AUC > 0.99). This allows the system to dynamically switch between neural drafting (e.g., EAGLE) and context-based copying. Our results across Llama and Qwen families demonstrate throughput gains of up to 15% over state-of-the-art baselines like EAGLE3, effectively turning copying from a noisy heuristic into a principled, model-aware decoding regime.

Roy Eisenstadt, Ido Cohen, Edo Cohen-Karlik +2

Tel Aviv University · Stealth Startup, Tel Aviv

Speculative Decoding LLM Inference Acceleration

Sep 16, 2026

ASPIRE: Asynchronous Batched Self-Speculative Decoding for Long-Context LLM Inference

Long-context LLM inference is bottlenecked by attention, whose repeated KV-cache reads make decoding memory-bound. Self-speculative decoding alleviates this by drafting tokens with sparse attention and verifying them with full attention, but existing batched methods remain synchronized: all requests in a batch share a single draft-verify schedule, even though the optimal draft length varies widely across requests and changes dynamically within each request. We propose ASPIRE, a non-synchronized batched self-speculative decoding framework built on three components. First, a unified mixed forward allows drafting and verifying requests to coexist in the same batched forward pass, removing the need for global draft-verify phases. Second, a lightweight online speculation scheduler uses per-request acceptance-rate estimates and a batch-aware cost model to let each request independently choose when to verify. Third, an intra-draft refresh layer performs full attention at a single designated layer during drafting, updating the sparse context at every draft step to reduce staleness during drafting. Across three models and five reasoning and long-context benchmarks, ASPIRE achieves

1.70

-

4.58\times

speedup in decoding throughput over autoregressive baselines and improves average speedup by approximately

27\%

over the strongest prior self-speculative baselines.

Amir Ziashahabi, Hossein Entezari Zarch, Lei Gao +2

University of Southern California, Los Angeles, CA, USA

Long-Context Language Model Inference LLM Inference Scheduling Speculative Decoding LLM Inference Acceleration

Sep 15, 2026

ECHO: Early-layer Collaborative Hierarchical Orchestration with Bonus Logits in Speculative Decoding

While draft-model-free speculative decoding offers a promising path to efficient LLM inference, it is frequently constrained by stale draft candidates and the high computational cost of the verification. To address these challenges, we propose ECHO, a hierarchical dual-loop framework that exploits the functional asymmetry between LLM layers. Leveraging the high discriminative efficiency of early layers and the authoritative distribution of final layers, ECHO bifurcates inference into a high-frequency inner loop and a low-frequency outer loop. Within the inner loop, early-layer bonus logits drive rapid, multi-step draft-tree exploration at a minimal cost. Simultaneously, the outer loop performs authoritative full-model verification through a state-reuse mechanism. Crucially, the outer loop also utilizes final-layer bonus logits to correct existing paths and supplement the tree with high-confidence candidates for subsequent cycles. Experimental results across diverse benchmarks demonstrate that ECHO significantly boosts mean accepted tokens and achieves a 2.4

\times

to 2.9

\times

speedup, outperforming existing state-of-the-art baselines with negligible engineering overhead and no extra deployment parameters, albeit with a one-shot fine-tuning dependency for optimal acceleration. The code is available at https://github.com/whucs21Mzy/ECHO.

Ziyang Ma, Zihong Zhang, Zuchao Li +4

School of Computer Science, Wuhan University, Wuhan, China · School of Artificial Intelligence, Wuhan University, Wuhan, China · 3Xiaomi, Beijing, China

Speculative Decoding LLM Inference Acceleration

Sep 15, 2026

LoopSpec: Pipelined Self-Speculative Decoding for Looped Transformers

Looped Transformers achieve strong performance with compact parameter sizes by repeatedly applying a shared stack of Transformer blocks across recurrent depths. However, they incur higher decoding latency than standard Transformer models of comparable parameter size because shared weights are accessed at every recurrent depth. To improve decoding efficiency, self-speculative decoding is particularly well suited to Looped Transformers, as their intermediate recurrent states can directly provide draft predictions without an auxiliary draft model. We therefore propose LoopSpec, a training-free self-speculative decoding framework tailored for Looped Transformers. LoopSpec extracts draft tokens from early recurrent states and operates in a pipelined manner, overlapping draft generation of future tokens with target verification of the current token. To improve draft accuracy without excessive compute overhead, we introduce a selective second proposal from deeper recurrent depth while ensuring lossless decoding under both greedy and sampling regimes. Furthermore, we derive the optimal proposal depths in closed form and show the prediction matches measurement. Across reasoning and coding benchmarks, LoopSpec achieves up to 6.83

\times

inference speedup across diverse Looped Transformers.

SangLyul Cho, Langqing Cui, Sehoon Kim +2

1Seoul National University · 2KAIST

Efficient Transformer Inference Speculative Decoding Recurrent Transformers

Sep 15, 2026

GrowMTP: Can RL Grow Its Own Draft Head?

Reinforcement learning (RL) post-training drives the frontier capabilities of large language models, with its wall-clock dominated by autoregressive rollout generation. Speculative decoding is an established remedy for this bottleneck, but existing draft heads must be pretrained or warmed up before RL, introducing substantial training cost outside the RL run to be accelerated. We observe that RL training itself provides both conditions required for online draft-head training: its rollout distribution is far narrower than that of pretraining, and its verification step continuously produces supervision signals aligned with this distribution. Building on these observations, we propose GrowMTP, which uses this supervision to train a draft head from scratch entirely within the RL loop, with all head updates detached from the policy backbone. On Qwen3-4B (no draft head), MiMo-7B-SFT (weak head), and Qwen3.5-4B-Base (strong head), GrowMTP achieves rollout speedups of 2.13x, 1.93x, and 1.36x, and end-to-end speedups of 1.60x, 1.41x, and 1.20x, respectively. GrowMTP therefore serves existing RL training frameworks as a modular component, particularly offering a from-scratch acceleration path for models without pretrained draft heads.

Minghua He, Lingzhe Zhang, Yuan Liu +2

WeChat AI, Tencent · Peking University

Speculative Decoding LLM Inference Acceleration RL Post-Training

Sep 14, 2026

Evaluating Losslessness in Speculative Decoding Under Finite-Precision Inference

Lossless speculative decoding is typically defined at the algorithmic level: a speculative procedure proposes multiple tokens and a verification procedure is designed to preserve the output trajectory of an autoregressive reference model exactly. In practical neural inference, however, this guarantee is implemented using finite-precision floating-point computations, and discrete token selection can amplify small numerical differences into divergent generation trajectories. We investigate this distinction using Orthrus, a hybrid autoregressive-diffusion architecture that performs self-drafting and self-verification within a frozen autoregressive backbone, as a representative case study. Across 1,190 prompts from 12 domains, exact trajectory matching under BF16 occurs for only 45% of the authors' checkpoint generations and 43% of those from our independently trained model. The probability of matching is strongly associated with the response-conditional perplexity of the autoregressive reference, indicating that trajectory divergence is not uniform across inputs. Despite these divergences, Orthrus does not exhibit systematic degradation on the evaluated downstream tasks. In contrast, FP32 inference yields exact trajectory matching on all evaluated prompts. These results demonstrate a gap between algorithmic losslessness and its implementation under finite-precision arithmetic, and motivate evaluating lossless speculative decoding at the level of exact generation trajectories as well as downstream task performance.

Ilya Koziev, Leonid Sinev, Ivan Oseledets

Speculative Decoding LLM Inference Acceleration Autoregressive Decoding

Sep 13, 2026

Carryover Drafting: Recycling Rejected States for Speculative Decoding

Speculative decoding accelerates LLM inference by verifying multiple drafted tokens in parallel, allowing a single target forward pass to accept several tokens. By construction, verification computes representations for both accepted and rejected tokens. Yet, conventional drafters retain only the representations of accepted tokens, leaving the substantial verifier computation spent on rejected tokens effectively wasted. We find that these discarded hidden states generated during target forward retain useful information about future tokens that can improve subsequent drafts. However, realizing this opportunity poses two distinct challenges. At inference, recycling overhead can increase drafting latency, diminishing the speedup gained from increased acceptance length. During training, standard parallel drafter training does not produce inference-aligned rejected states, while obtaining them through sequential rollouts would sacrifice parallelism across training positions. We introduce Carryover Drafting, which addresses both challenges. Carryover recycles rejected target hidden states as temporary KV context, allowing the drafter to selectively attend to them. It reuses the drafter's existing interface and adds only a single learned embedding to distinguish rejected states from committed context. The additional KV context is replaced each drafting round, keeping its length bounded by one proposal block. We introduce parallel draft--verify--draft training that exposes the drafter to inference-aligned rejected states while preserving parallelism across training positions. Experiments with DFlash and a DSpark-derived semi-autoregressive drafter across two target models show that this simple Carryover mechanism improves average acceptance length by 6.5--14.7% and end-to-end vLLM speedup by 7.9--14.4% over the corresponding baselines, with speedup gains reaching 28.8% on translation.

Jahyun Koo, Sunghyeon Woo, Jaeeun Kil +4

Seoul National University · NAVER Cloud

Speculative Decoding LLM Inference Acceleration

Sep 8, 2026

Osprey: Target-agnostic Pre-training Makes Stronger Drafters in Speculative Decoding

Speculative decoding is critical for accelerating LLM inference. However, the speedup is fragile: drafters are typically trained against a narrow distribution for a single target model, and their acceptance rate collapses under workload shifts. This is a striking inversion of modern LLM development, where target models are valued precisely for the broad generalization they acquire through large-scale pretraining. We argue that the natural remedy, pretraining, has been hard to apply to drafters because existing recipes are target-specific: the drafter consumes the target's hidden states and is distilled on the target's logits, so pretraining must be repeated for each target. We introduce Osprey, which instead bootstraps drafters from off-the-shelf pretrained small language models, treating broad pretraining as a reusable, target-agnostic asset and reducing per-target work to a lightweight adaptation step. Realizing this requires overcoming two challenges: small LMs are far deeper than a latency-bound drafter can afford, and their pretrained computation must remain intact while the drafter learns to ingest target hidden states and emit tokens in the target's vocabulary. Osprey addresses both by pruning to a shallow backbone, restoring its language-modeling capability with target-agnostic next-token pretraining, and adapting it to each target through vocabulary alignment, zero-initialized QKV expansion, and distillation from the target model's output distribution. Empirically, a single pretrained Osprey backbone transfers across targets and improves mean acceptance length by 16.1% for Qwen3-8B, 21.2% for Llama-3.3-70B-Instruct, and 22.7% for the 229B MiniMax-M2.5 (with 17.5% higher tokens per second), with the largest gains on out-of-domain and multilingual data. Our code is available at https://github.com/LeanModels/Osprey.

Fengxiang Bie, Yuqing Jian, Yifan Yu +7

Together AI · The University of Sydney, Australia · University of Illinois Urbana-Champaign, USA +1

Language Model Pretraining Speculative Decoding LLM Inference Acceleration

Sep 7, 2026

Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training

Speculative decoding accelerates rollout generation, which dominates the cost of reinforcement learning (RL) post-training. Online co-training can further increase the draft's accuracy, yielding greater speedups. However, scaling this approach to co-training on large models with long contexts poses two obstacles: (1) branch attention is unsupported by standard causal context-parallel (CP) implementations, and (2) target features span across pipeline-parallel (PP) stages. We address both with an end-to-end system for large-scale online draft co-training. For CP, we extend packed, load-balanced zigzag ring attention by merging rank-local branch attention with causal main-sequence attention. For PP, TapChannel transports intermediate target features across stages via a separate path, leaving the pipeline schedule unaffected. Experiments demonstrate that co-trained drafts closely track the policy baseline while delivering substantial rollout and end-to-end speedups across model scales up to 122B. Our CP design achieves strong scaling at 256K tokens with significant memory savings over prior work, and our PP transport incurs modest overhead. Code can be found at https://github.com/NVIDIA-NeMo/RL/issues/3698.

Zili Wang, Zhaopeng Qiu, Yuekai Zhang +2

NVIDIA

Context Parallelism Speculative Decoding LLM Inference Acceleration RL Post-Training

Sep 4, 2026

SJD-SV: Speculative Jacobi Decoding with Semantics Verification for Autoregressive Image Generation

Speculative Jacobi Decoding (SJD) is an important approach for accelerating autoregressive image generation. Although SJD has shown superior performance, recent studies point out that it usually suffers from a token ambiguity issue during token verification but its reason can not be well explained. To figure out this reason, in this paper, we conduct a visualization analysis on vision token and find that different from text tokens, vision tokens generally corresponds to some local, small, and unclear vision details, which means only using single token is difficult to accurately express a certain semantic, thereby causing token ambiguity issue. To this end, we propose a novel Speculative Jacobi Decoding with Semantics Verification (called SJD-SV), for accelerating autoregressive image generation. The key idea is that leveraging the strong correction characters between tokens to recognize semantic-aware token subsequence and then instead of perform token-by-token verification, turning to perform verification on semantic-aware token subsequence level for accelerating image generation. In particular, our method is plug-in, which can be directly integrated into existing SJD and its variants. Extensive experiments on various datasets show that existing SJD methods achieve significant performance improvement after integrating our SJD-SV method.

Baoquan Zhang, Bingqi Shan, Shihao Fang +3

Shenzhen Key Laboratory of Internet Information Collaboration, Harbin Institute of Technology, Shenzhen · Pengcheng Laboratory, Shenzhen

Speculative Decoding Autoregressive Image Generation

Sep 2, 2026

Jina-OCR-v1: Efficient Document Parsing with Speculative Decoding and Dense Verifiable Rewards

We present Jina-OCR-v1, an end-to-end document parsing model built to serve on low-budget GPUs. It combines the compressed-vision encoder and the 3B mixture-of-experts decoder of DeepSeek-OCR, which activates about 570M parameters per token, with a FastMTP speculative decoding head that shares a single draft block recursively across K=3 prediction steps. Greedy verification makes decoding lossless. Post-training combines instruction alignment, robustness fine-tuning on difficult documents, and GRPO under dense verifiable rewards: deterministic formula, table, and structural checks that award partial credit. The training data mixes cleaned public corpora with targeted synthetic pages. At the default dynamic-resolution setting, Jina-OCR-v1 scores 91.14 on OmniDocBench v1.6 and 83.4 on olmOCR-Bench, and reaches the highest page throughput in our comparison at 2.57 pages per second. On a low-budget GPU such as the NVIDIA L4, FastMTP doubles decoding speed over greedy autoregressive decoding. The model is publicly available at https://huggingface.co/jinaai/jina-ocr-v1.

Alejandro Barón García, Feng Wang, Emilia Garcia Casademont +1

Jina AI by Elastic · New Montgomery Street, San Francisco, CA 94105, USA

Efficient VLM Inference Speculative Decoding Optical Character Recognition Document Image Understanding

Sep 1, 2026

SFAD: Speculative Factuality-Aware Decoding

As one of the most critical challenges in large language models, contextual faithfulness directly determines their reliability in knowledge-intensive applications. This task is particularly challenging as it requires balancing factual consistency with generation efficiency. Contrastive decoding methods require dual forward passes (with and without context) to compare model outputs, doubling inference computational overhead, while post-training alignment demands extensive reinforcement learning with substantial computational overhead. To address this challenge, we present SFAD, a speculative decoding framework that enhances contextual faithfulness without inference degradation. We first construct ConFide, a preference dataset with fine-grained atomic perturbations, to train a context-faithful draft model via Direct Preference Optimization. During inference, Epistemic Friction detects potential hallucinations by quantifying distributional tension weighted by specialist certainty. When friction exceeds the threshold, Asymmetric Logit Steering refines the target distribution through residual-based logit injection; otherwise, standard speculation proceeds. Extensive experiments demonstrate that SFAD substantially improves faithfulness while achieving

2.48\times

speedup, offering a practical solution for efficient LLMs.

Guanqiao Chen, Di Wang, Lijie Hu

1MBZUAI · University of Science and Technology of China · 3Provable Responsible AI and Data Analytics (PRADA) Lab +1

LLM Hallucination Mitigation Speculative Decoding LLM Inference Acceleration

Aug 31, 2026

Vision Is Not Overhead: One-Pass Block Drafting for Lossless Speculative Decoding in Vision-Language Models

Speculative decoding accelerates generation without changing its output, but on vision-language models (VLMs) a self-reinforcing cycle holds it back. Because an autoregressive drafter pays a sequential pass for each drafted token, it must stay small and can ill afford to attend to the image at each pass. Prior work therefore compresses or hides the image, leaving the drafter weakest on the text the image determines. We present GLANCE, a one-pass block drafter that breaks this cycle on an unmodified VLM target. Its block-diffusion head drafts a whole block in one forward pass over the target's already fused vision-language states, reading the multimodal context once, however deep the draft. The target verifies a wide candidate tree in one pass and commits exactly its greedy output. In one production engine at a fixed round budget, GLANCE decodes up to 3.05 times faster than autoregressive decoding and outpaces the production EAGLE3-VL head on average and by about 11% on grounded tasks. An entropy law explains when drafting pays, predicting the longest accepted blocks on grounded tasks, where the target's next-token entropy is lowest. Our code is available at https://github.com/js-lee-AI/GLANCE.

Jungseob Lee, Seongtae Hong, Dongyub Jude Lee +4

Korea University · Zoom Communications · Soongsil University +2

Efficient VLM Inference Speculative Decoding

Aug 31, 2026

Ceiling-Clipped Acceptance Histograms Indicate Stranded Speed-up in Block-Diffusion Speculative Decoding

Speculative decoding speeds up generation with an efficient draft model (drafter) that proposes tokens for a target model to verify in one pass, preserving the target's output distribution. High-acceptance block-diffusion drafters such as DFlash and DFlare fill an entire block in one parallel pass. In many cycles, the target accepts the whole block, so the drafter exhausts its trained block horizon before verification fails. We call this unrealized acceptance stranded speed-up. A mean committed length, per prompt or per cycle, hides it, whereas the acceptance histogram exposes it as a spike in the ceiling bin, the fraction of cycles that accept the entire block. We recommend the histogram as a preflight check before spending training compute. Naively widening the block at inference does not recover the speed-up, because once the block outgrows its training size, the drafter's bidirectional attention shifts its distribution even at early positions and erodes front-of-block verification. Instead, we post-train the drafter on a longer block with a short curriculum that emphasizes the newly exposed positions, a method we call DBloom. Expanding the pretrained DFlash and DFlare drafters from block size 16 to 24 across Qwen3-8B and Qwen3-4B targets raises the per-prompt committed length on the high-ceiling benchmarks by a median of +0.8 tokens (up to +1.1). Once continuation fine-tuning precedes expansion, the increase reaches 1.37 tokens. The same expansion also lifts committed length on all seven benchmarks for Gemma-4-12B-IT, a different model family, by a median of +0.41 tokens (Arm A), and the full continuation-then-expand pipeline (Arm B) adds +0.29 to +0.98 tokens over the same B16 drafter. In a prompt-matched comparison against JetSpec, a contemporary tree-based drafter not used in our design, DBloom commits more tokens on every benchmark at tree budgets up to 64 nodes.

Ephrem Wu

Advanced Micro Devices, Inc., USA

Speculative Decoding Diffusion Language Model Decoding Diffusion Model Inference Acceleration

Aug 31, 2026

Strong Drafts Need Compact Memories: Long-Context Speculative Decoding with Compressed KV Cache

Long-context LLM applications such as document summarization and multi-turn agents require generation from prefixes spanning tens of thousands of tokens, making decoding latency a major bottleneck. Speculative decoding (SD) reduces latency without changing model outputs, but its speedup depends on both accepted draft tokens and draft-step latency: Lightweight drafts are fast but lack the capacity to capture long-range dependencies, whereas strong independent drafts recover acceptance but incur growing KV-access cost at long prefixes. We introduce memory-augmented drafting for long-context SD, equipping a strong independent draft with compressed draft-side KV memory: A lightweight adaptor constructs and incrementally updates this memory to retain distant information and exact recent context. The target verifier retains its full KV cache and applies the standard accept/reject rule, preserving SD's lossless guarantee. Experiments on Llama~3.1-8B and 70B targets at prefix lengths up to 32K show that our method reduces draft-side memory by over 70%. It achieves speedups of up to 2.08x and 3.33x , respectively, over autoregressive decoding.

Tong Yuan, Chengxi Liao, Zeyi Wen

Data Science and Analytics Thrust, Information Hub, The Hong Kong University of Science and Technology (Guangzhou)

Memory-Augmented Language Models KV Caching Speculative Decoding LLM Inference Acceleration KV-Cache Compression Long-Context LLM Inference

Aug 31, 2026

Verification-Aware Training for Speculative Decoding

Speculative decoding accelerates large language model inference by using a draft model to generate candidate tokens, which are verified by the target model in a single forward pass. Verification proceeds sequentially and discards every position from the first rejection onward, yet existing draft training relies on token-level imitation of the target with a fixed per-position weighting that reflects neither property. We introduce Verification-Aware Training (VAT), a plug-in framework that simulates verification at every training step and turns the resulting accept and reject patterns into supervision. VAT consists of two components: (i) a verification head, a lightweight jointly trained binary classifier that supervises the draft model on whether each position survives sequential verification; (ii) verification-adaptive weighting, which replaces the fixed weighting schedule by keeping full weight up to each sample's first rejection point and re-anchoring the decay to start there. VAT modifies only the training objective, so it can be layered on top of existing methods without changing the draft architecture, the target model, or the inference procedure. Applied to EAGLE-3 and DFlash on Qwen3-4B, Qwen3-8B, and LLaMA-3.1-8B, VAT improves average acceptance length by up to 11.4% and wall-clock speedup by up to 8.7%, with consistent gains across math, code, and chat benchmarks. Code will be available at https://github.com/naver-ai/vat

Geonmo Gu, Byeongho Heo, HeeJae Jun +4

NAVER AI Lab · NAVER AI Search Platform · Korea University

Speculative Decoding LLM Inference Acceleration

Aug 30, 2026

ReTrace: Rejected-Trajectory Conditioning for Speculative Decoding

Speculative decoding accelerates autoregressive language model inference by having a lightweight draft model propose multiple candidate tokens, which are then verified in parallel by a larger target model. However, after the first rejection, standard prefix-based verification discards the remaining draft suffix, so the computation spent generating and verifying those positions does not contribute to decoding progress. Focusing on DFlash, we show that rejected positions in a rejected suffix may still align with the target continuation, indicating that the draft model can retain useful semantic and structural information despite local token-level errors. Motivated by this observation and inspired by conditional diffusion, we introduce ReTrace, a rejected-trajectory conditioning method that conditions each draft block on the rejected suffix from the previous round rather than generating it from fresh mask placeholders alone. ReTrace retains the hidden representations of the rejected suffixes, aligns them with the next draft block, refines them using target-aware correction signals from the same verification pass, and admits them into the drafter's input embeddings through gated residual fusion. Because rejected tokens are never committed and target-side verification remains unchanged, ReTrace preserves the lossless property of speculative decoding without requiring an additional model forward pass. Experiments with Qwen3 models across mathematical reasoning, code generation, and open-ended dialogue demonstrate that ReTrace consistently improves average acceptance length and end-to-end decoding speed over its DFlash backbone. By introducing cross-round conditioning without modifying within-round proposal generation, ReTrace is largely orthogonal to existing drafting improvements and might be combined with them for further gains.

Luxi Lin, Zhanpeng Zeng, Shuang Peng +2

1Xiamen University, 2ByteDance

Speculative Decoding LLM Inference Acceleration

Aug 28, 2026

A rigor-matched audit of periodic-step layer skipping for efficient llm inference: conflayers versus swift, with a supplemental analysis of trained routing alternatives

Layer-skipping methods for efficient LLM inference decide, at some granularity, which transformer layers to execute for a given input. We present a rigor-matched, three-seed audit of two periodic-step, search-based methods that make this decision online at inference time and re-evaluate it every few generation steps: a confidence-gated early-exit baseline (ConfLayers) and genuine self-speculative decoding (SWIFT, Xia et al. 2024), together with vanilla autoregressive decoding, across Qwen2.5-0.5B and Qwen2.5-1.5B (Yang et al. 2024) on GSM8K (Cobbe et al. 2021) and CNN/DailyMail (Nallapati et al. 2016; See et al. 2017). SWIFT is strongest on accuracy in three of four cells, while ConfLayers is dominated everywhere, with particularly large deficits on GSM8K at 1.5B. Separating online-search overhead from pure inference cost, we find that SWIFT's true inference speed is faster than ConfLayers's in all four cells (5-21%), reversing the naive wall-clock ranking in three; ConfLayers's search overhead is small and stable (1-2% of cost), whereas SWIFT's is larger and more variable across seeds (up to 28.7%). We additionally examine two trained routing methods, LayerRoute (Sikdar, 2026), a per-sequence, input-conditioned hard gate, and LayerDrop (Fan et al. 2020), a fixed, input-independent pruning pattern, as a supplemental analysis rather than a head-to-head comparison because both operate at a coarser decision granularity. Under a verified protocol with genuine per-input gating, a genuine full-model baseline, and genuine inference-time compute skipping, both show modest real speedups (1.08-1.33x) but accuracy well below the periodic-step methods, including near-total LayerRoute collapse on GSM8K at 1.5B (0.003 mean exact-match across three seeds). We release the full audit protocol as a template for rigor-matched efficiency comparisons.

Prateek Kumar Sikdar

Accenture

Layer Skipping in Language Model Decoding LLM Inference Acceleration Efficient Language Model Inference Inference-Time Search Speculative Decoding

Aug 27, 2026

Beyond Parallel Blindness: Information Floors and Model Gaps in Block Drafting

Block drafters propose several tokens in one forward pass, before earlier target tokens are realised. Their rejection mixes two losses: missing within-block path information and imperfect modelling of observable information. Accepted length cannot distinguish them. We separate the two with an information floor, the minimum expected rejection at a specified conditioning order; rejection above this floor is the model gap. Measurements across four domains and four open-weight targets, plus floor estimates on a frontier API target, yield three findings. First, the all-parallel floor reaches

0.286

at the final slot on Qwen3-4B, limiting even the best proposal to

71\%

per-slot acceptance. Second, one realised token removes

86

--

100\%

of this floor, a locality also recovered by an independent mutual-information analysis. Third, current drafters remain far above their floors: the final-slot model gap accounts for

43

--

64\%

of DFlash rejection and

85

--

92\%

of DSpark's oracle-conditioned rejection. Guided by this separation of short-range conditioning from proposal quality, we replace a context-independent predecessor correction with a prefix-attention head that reads committed context conditional on the predecessor. With supporting backbone components, the resulting Qwen3-4B drafter improves mean serving accepted length by

3.93\%

over the released DSpark checkpoint across nine tasks, without increasing the conditioning order. Code and data: https://github.com/tie-pilot-qxw/specfloor; drafter checkpoints: https://huggingface.co/TIE-Pilot/dspark-attnconv-block7-qwen3-4b.

Xinwei Qiang, Xiang Fang, Chang Chen +3

University of California San Diego

Speculative Decoding LLM Inference Acceleration Parallel Decoding

Aug 27, 2026

Trajectory-Level Speculative Decoding for Diffusion Language Models

Diffusion-based language models (dLLMs) enable parallel token generation through iterative denoising, but existing decoding strategies collapse to single-token generation under low confidence, severely limiting throughput. Unlike autoregressive models where speculative decoding operates on token sequences in a fixed left-to-right order, dLLMs require speculating over denoising trajectories-sequences of multi-token updates with explicit positions and unmasking orders. We develop a trajectory-level speculative framework that constructs draft denoising trajectories via confidence-stratified tree exploration and verifies them through blockwise parallel evaluation with bidirectional attention masking. Our method further introduces inter-block speculation, exploiting diffusion models' bidirectional structure to perform cross-block lookahead. We formally characterize when this approach is exact and identify trajectory drift as the fundamental cost of increased parallelism. Building on Fast-dLLM's dual-cache infrastructure, our framework reduces denoising iterations by 30-40% and increases tokens-per-step from 2.6 to 4.3, achieving 7-14x speedup over vanilla dLLMs and 1.3x over Fast-dLLM with less than 1% accuracy change across reasoning and code benchmarks.

Tianxiang Pan, Baitao Gong, Mo Guang +5

Li Auto Inc., Shanghai, China

Speculative Decoding for Diffusion Language Models Diffusion Language Model Decoding Speculative Decoding Diffusion Language Model Inference

Aug 26, 2026

AsymSpec: Context-Asymmetric Speculative Decoding for Agentic LLMs

Agentic LLM pipelines face escalating inference costs as context accumulates across retrieval, tool use, and multi-turn interactions. To control latency, deployments routinely compress inputs, but this degrades task accuracy. Speculative decoding (SD) accelerates generation losslessly, yet it assumes the drafter and verifier share an identical context, preventing SD from resolving the accuracy-overhead trade-off. We propose AsymSpec, an asymmetric speculative decoding framework that breaks this symmetry: a lightweight drafter reads the full input while the large verifier operates on the compressed view. The drafter steers the verifier via a contrastive

δ

-fusion of logits, modulated by a divergence-aware acceptance gate that preserves verification stability and high draft acceptance rates. Evaluated across four agentic capabilities and two end-to-end agent benchmarks, AsymSpec reaches

\approx 90\%

of full-context accuracy on average, delivering

1.3

--

1.7\times

throughput speedups at

0.2

--

0.3\times

the compute cost on isolated text capabilities. These results show that asymmetric context access yields substantial gains precisely when compression discards critical reasoning signals.

Sheng Liang, Yongyue Zhang, Nathanael Brian +4

Huawei Technologies Co., Ltd. · University of Science and Technology of China

Speculative Decoding LLM Inference Acceleration

Aug 26, 2026

The Limits of Speculation: Bounding Speculative Decoding in Mixture-of-Experts

Speculative decoding in Mixture-of-Experts (MoE) models faces the problem of unstable verification cost caused by input-dependent expert loading. To study the physics of this process, we formulate speculation-budget selection as an offline Stochastic Shortest Path (SSP) problem over reference sequences and build a diagnostic Oracle that uses counterfactual simulation to account for MoE verification cost. A detailed analysis of the Oracle's decisions on the Qwen3-Coder and EAGLE-3 pairing, in the space of marginal deltas (Delta Space), shows that rejected candidates form a strict linear boundary. This result demonstrates that a complex global optimization is locally governed by a necessary condition balancing marginal cost against expected progress (

\frac{Δ\mathbb{E}[Cost]}{Δ\mathbb{E}[a]}

), providing a rigorous mathematical reference point for designing future adaptive online heuristics.

Aidar Amankulov, Denis Mamatin

Speculative Decoding Mixture-of-Experts Inference

Aug 25, 2026

ResiSpec: Enhancing Multi-Candidate Speculative Sampling via Residual Distribution Shaping

The efficiency of Large Language Model (LLM) serving is fundamentally limited by the sequential nature of autoregressive decoding. Speculative Decoding (SD) mitigates this by using a lightweight draft model to speculate future tokens, which are then validated by the LLM in a single parallel forward pass. To further boost efficiency, multi-candidate schemes propose diverse candidate sets to increase the likelihood of token acceptance. However, we show that these schemes are bottlenecked by Residual Drift: a phenomenon where the rejection of initial candidates causes the residual target distribution to diverge from the draft model's predictions. This shift renders subsequent candidates ineffective and forces the system into expensive resampling. To resolve this, we propose ResiSpec, a framework that strategically reforms the proposal distribution during verification to anchor the residual target mass within the draft model's high-confidence regions. By mathematically re-aligning the verification process without compromising output exactness, ResiSpec prevents candidate obsolescence and achieves up to 1.92

\times

speedup over state-of-the-art multi-candidate methods. Code is available at https://github.com/Czzzk/Resispec.

Zhi-Kai Chen, Jun-Jie Tao, Wei-Xiang Mao +2

School of Artificial Intelligence, Nanjing University, China · National Key Laboratory for Novel Software Technology, Nanjing University, China · Nanjing University, China

Speculative Decoding LLM Inference Acceleration

Aug 25, 2026

AgentSpec: Speculative Decoding for Batch Inference of LLM Agents

Large language model (LLM)-based agent applications often incur high response time. Speculative decoding is a promising solution to improve the inference efficiency of LLM agents without impacting generation quality. However, state-of-the-art speculative decoding algorithms exhibit substantial speed degradation under large batch sizes, limiting their effectiveness to deploy in real-world agent applications. In this work, we first present a systematic analysis of speculative decoding for LLM agents and identify two dominant factors of speedup degradation: high rejection rate of speculative tokens, and under-utilization of dynamic token budgets.B ased on these observations, we propose AgentSpec, a speculative decoding algorithm that addresses the limitations of existing methods for LLM agents. AgentSpec incorporates structure-isolated drafting that constrains speculation to semantically coherent segments of the agent workflow, reducing the drafts of irrelevant semantic paths and achieving an extremely low rejection rate. Moreover, AgentSpec adopts redundancy-aware budget allocation that exploits agent-level information to better utilize the dynamically-free token budget during the agent inference. We implement and evaluate AgentSpec on five different workloads and four different models from four different LLM families in vLLM. Our results demonstrate the superiority of AgentSpec over state-of-the-arts.

Xin Wang, Ziming Miao, Yi Zhu +4

The Ohio State University · Microsoft Research · University of Michigan

Speculative Decoding LLM Inference Acceleration LLM Agent Serving

Aug 21, 2026

TreeWY: Speculative Verification for Gated DeltaNet Hybrids

Modern open models are hybrids: most layers are linear-attention (Gated DeltaNet, GDN) layers carrying a small fixed-size recurrent state instead of a growing key-value (KV) cache. This makes ordinary decoding memory-efficient, but hurts speculative decoding. To verify a batch of draft tokens and then roll back the rejected ones, today's systems snapshot the full recurrent state at every draft position for GDN layers, and those snapshots cannot be shared across branches of a draft tree, so a wide, high-acceptance tree becomes memory-infeasible. We remove the snapshots. Using a tree-structured WY transform of the gated delta rule, we compute every draft node's output with a single triangular solve and reconstruct only the one accepted state on commit, storing a small pseudo-value matrix instead of per-node states; the derivation depends only on the gated delta rule, not on any other architectural detail. In serving benchmarks on two scales of one hybrid model family (Qwen3.5 35B and 397B) this cuts speculative recurrent-state memory and KV-cache pressure at essentially identical acceptance length, turning the freed HBM into higher throughput and much lower time-to-first-token (TTFT) wherever memory binds, and costing a few percent where it does not. For tree width the same memory buys affordability: a wider, higher-acceptance draft becomes possible, though not yet a throughput win.

Sneha Murthy Ghantasala

Thomson Reuters

Speculative Decoding LLM Inference Acceleration Memory-Efficient Inference Gated Delta Networks Delta-Rule Linear Attention

Aug 21, 2026

Is Multimodal Speculative Decoding Ready for Diffusion-Based Parallel Drafting? A Survey and Empirical Diagnosis

Speculative decoding accelerates autoregressive generation by allowing a lightweight drafter to propose future tokens while a target model verifies them in parallel. Its lossless guarantee has motivated a line of work that pushes the drafter itself toward parallel generation. The most recent paradigm is block-parallel generative drafting, including diffusion-based methods such as DFlash and DSpark, achieving up to 3.6x speedup on common daily chatting tasks. While this transition is well studied in text-only LLMs, its applicability to multimodal models remains an open question. Existing multimodal speculative decoding efforts focus on input compression, adapter alignment, candidate coverage, or modality-specific verification; however, block-parallel generative drafting remains largely unexplored. To bridge this gap, this paper combines a modality-centered survey with a cross-architecture empirical study to ask: Is multimodal speculative decoding ready for diffusion-based parallel drafting? In this survey, we systematically analyze a wide spectrum of multimodal models, spanning Vision-Language, Video-Language, Audio, and Vision-Language-Action (VLA) architectures, from the dual perspectives of drafting parallelism and cross-modal information interaction. We introduce a unified taxonomy that isolates drafter-side parallelism from orthogonal design choices such as tree construction and verification strategies. Furthermore, we provide a comprehensive empirical comparison of existing methods under varying degrees of parallelism across standardized multimodal benchmarks, including OCR, VQA, visual reasoning, and image captioning. Finally, we summarize the limitations of current approaches, discuss open challenges, and outline promising future directions for this rapidly evolving field.

Yantao Li, Huanlin Gao, Fang Zhao +12

National Key Laboratory for Novel Software Technology, Nanjing University · Data Science & Artificial Intelligence Research Institute, China Unicom · Unicom Data Intelligence, China Unicom

Speculative Decoding Speculative Decoding for Diffusion Language Models

Aug 20, 2026

LiLiCorr: Lightweight Likelihood Correlation of Parallel Drafts for Speculative Decoding

Speculative decoding accelerates language-model inference by drafting future tokens the target model verifies in parallel. A diffusion-style drafter such as DFlash drafts an entire block in one forward pass. It is trained on the per-position marginals rather than on the joint distribution over the block, so the tokens it emits are individually plausible yet jointly incoherent. We introduce LiLiCorr, a Lightweight Likelihood-based model that Correlates the per-position marginals such a drafter produces. It keeps the top-K tokens at each position and processes them jointly, emitting an in and an out vector for each. Two candidates at consecutive positions match when the earlier out vector aligns, in cosine similarity, with the later in vector. Training scores the correct pairings highest and pushes competing ones down, so coherent blocks outscore incoherent ones. The joint distribution over the block, exponential in its length, is never materialized. One lightweight network pass produces all the vectors, the pairwise scores follow as batched matrix operations, leaving only a cheap greedy walk sequential. We co-train the DFlash drafter with LiLiCorr, so it proposes candidates that correlate into longer accepted sequences. Over the vanilla DFlash drafter it builds on, LiLiCorr accepts more and serves faster at all 72 settings we test: nine benchmarks at two target sizes under greedy and temperature-one decoding, plus a throughput sweep over six concurrencies, two input lengths and three output-entropy tiers. It raises acceptance length by 7 to 19%, while its single-pass scoring head costs only about 3% of the per-block latency. Against three concurrently developed methods that also restore coherence at draft time, all equally optimized on a common stack, LiLiCorr holds the highest throughput in 63 of those settings, ties within a measured noise floor in 6, and trails in only 3.

Matan Rusanovsky, Yoav Miron, Roy Uziel +5

NVIDIA

Speculative Decoding LLM Inference Acceleration Diffusion Language Model Decoding