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
Farhana Amin, Sabiha Afroz, Dimitrios S. Nikolopouloscs.AI
Diffusion language models can generate many tokens in parallel, but they still require repeated denoising steps during inference. This makes generation costly, especially when the model continues to recompute tokens that are already stable. To address these limitations, we propose CAI-DLLM, a training-free inference method that uses first-step confidence to guide denoising and reduce inference time. Specifically, CAI-DLLM commits easy tokens earlier, allocates more denoising steps to harder tokens, and adjusts decoding schedules across output blocks. As it relies only on first-step confidence signals, it does not require retraining, extra predictors, or weight updates. We evaluate CAI-DLLM on LLaDA-8B-Instruct and Dream-7B-Instruct across math, code, reasoning, commonsense, and long-context tasks. CAI-DLLM achieves up to 18.2x wall clock inference speedup on LLaDA GSM8K while improving accuracy from 76.27% to 77.41%, and up to 13.1x speedup on Dream HumanEval while achieving higher pass@1 than no-cache inference, 48.17% compared with 46.95%. On harder reasoning tasks, speedups reach 44.8x, with a largest accuracy drop of 4.4 points, while energy consumption is reduced by up to 95.3%.
Diffusion Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive language models, offering the potential for substantially faster inference through parallel decoding. Existing parallel decoding schedulers typically commit positions only after they meet a per-position criterion, overlooking how early commitments may benefit subsequent decoding. We identify a ripple effect in dLLM decoding: proactively committing a mid-entropy pivot position can induce a pronounced reduction in uncertainty across the remaining masked positions. This uncertainty reduction allows subsequent steps to unmask more tokens in parallel, thereby accelerating the overall decoding process. To exploit the ripple effect, we propose Ripple-Pivot Search (RPS), a novel training-free decoding method that seeks mid-entropy positions as promising candidate pivots (where to decode), and determines their token assignment that yields the greatest downstream benefit via lookahead evaluation (what to decode). Across 3 dLLMs and 4 reasoning and code-generation benchmarks, RPS achieves 4-10$\times$ wall-clock speedup over the standard decoder while preserving generation quality, and improves accuracy over the previous lookahead baseline by up to 5.49% while delivering higher throughput in most settings. When integrated with KV caching, RPS further achieves up to 18$\times$ wall-clock speedup over the standard decoder.
Diffusion language models (DLMs) iteratively refine a sequence, allowing earlier predictions to be revised as context evolves. This rollback capability distinguishes them from irreversible autoregressive generation, but makes inference costly. Every denoising update alters the global context, forcing both prompt and response states to be recomputed even though only response tokens are revisable. Key-value (KV) caching could reduce this cost, yet conventional caching assumes immutable historical states and is therefore difficult to reconcile with rollback. In this paper, we introduce Adaptive Reuse of Cached Hidden States for Efficient Rollback (Archer), a training-free KV caching method for rollback-capable DLMs. Archer asymmetrically keeps the mutable response synchronized with the current hypothesis while reusing prompt K/V within a bounded state neighborhood. Although prompt representations also change under bidirectional attention, their token identities remain fixed; bounded reuse therefore amortizes repeated prompt computation without caching mutable response states. It also delays feedback from tentative tokens, reducing premature reinforcement of transient high-confidence errors and giving rollback more opportunity to correct them. Our analysis characterizes prompt reuse as a reversibility-aligned cache boundary, bounds its state-dependent approximation error, and gives a decoder-margin condition for preserving full-refresh decisions. Existing DLM acceleration often trades quality for speed. Archer shifts this frontier, attaining the best mean performance of 33.63% together with a 2.57x mean speedup on the main suite. Across evaluated settings, it improves Pass@1 by up to 3.05 points and reaches up to 2.95x speedup. Controlled analyses connect the quality gain to delayed prompt feedback and validate state-aware refresh. Our code is available at https://github.com/Hxnng/Archer.
Multi-Token Prediction (MTP) has emerged as an effective paradigm that augments a shared Large Language Model backbone with auxiliary heads, training the model to predict several future tokens in parallel to enrich its supervision signal and accelerate inference. However, existing training frameworks adopt a rigid, fixed-length prediction horizon, disregarding the highly non-uniform information density of natural language and code. Forcing the auxiliary heads to predict across high-entropy semantic boundaries injects noisy, conflicting training signals; because these heads share the backbone's latent representations, the resulting gradients backpropagate and interfere with the model's core capabilities. We propose AdaMTP, an adaptive training paradigm that dynamically aligns the prediction horizon with the intrinsic predictability of the sequence. At its core, an entropy-based segmentation algorithm leverages the base model to detect sudden surges in uncertainty as semantic boundaries, partitioning sequences into variable-length groups. Each token is assigned an adaptive prediction depth, and a dynamically masked MTP objective suppresses the loss for predictions that cross these boundaries, attenuating the noisy gradients that degrade the backbone. Across mathematical reasoning, code generation, and general benchmarks on three backbones (Llama-3.1-8B, Qwen-2.5-7B, Gemma-3-12B), AdaMTP consistently outperforms standard MTP in both task performance and inference speedup.
Diffusion language models (DLMs) update many tokens in parallel, yet practical decoders often use a fixed denoising horizon. Many predictions stabilize early, but blockwise decoding continues until all positions are resolved, causing repeated dense forward passes. Existing accelerators often rely on learned filters, modified scores, dependency models, or cache-specific mechanisms. We ask whether native trajectory signals can identify residual positions likely to match the deterministic dense endpoint. We propose CORA-Diff, a training-free method that preserves the original transfer rule and applies confidence-and-persistence gating only to positions that rule leaves unresolved. Accepted tokens remain visible as context, and the block terminates once all positions are resolved. This requires no backbone change, learned acceptance model, or logit modification. Our theory explains why high-confidence, persistent predictions are more likely to match the fixed-horizon dense endpoint, and paired post-intervention trajectories provide direct empirical support. We select one operating point on a separate GSM8K calibration subset and freeze it for all evaluations. Under a matched Learn2PD-style LLaDA protocol, CORA-Diff has the lowest measured runtime in all eight task-length settings. Task scores match or exceed dense decoding in five settings, and the largest observed drop is 1.22 points. Its incremental speedups over EOS-aware dense decoding are 2.70x and 3.32x on GSM8K and HumanEval. It also reaches 13.14x under the fixed-horizon 1024/1024 mechanism-isolation protocol and transfers to Dream without retuning at 3.18x-3.53x. These results show that native confidence and persistence enable reliable residual acceptance, reducing repeated denoising computation while preserving task quality.
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.
Block-wise diffusion large language models (dLLMs) decode sequentially at the block level, enabling effective KV-cache reuse across blocks but making inter-block decoding strictly serial. Prior work has attempted to unlock inter-block parallelism through post-training methods, but achieves only modest speedups and often degrades accuracy. We observe that self-correcting dLLMs offer a training-free alternative: token-to-token (T2T) editing can repair tokens drafted with a slightly stale upstream context, so a downstream block requires only an informative draft rather than a finalized predecessor. This turns block finality from a hard dependency into a scheduling resource. We propose \textbf{\flowblock{}}, a training-free parallel decoding framework built on two mechanisms. (i) \emph{Gated Wavefront Decoding} admits blocks into a bounded wavefront only when a readiness gate is satisfied, jointly refines active blocks via T2T editing, and commits blocks in order under a windowed block-causal mask that preserves exact frozen-prefix KV caches reuse. (ii) \emph{Heterogeneous Wavefront Packing} assigns each request an independent wavefront while packing asynchronous windows into dense, shape-stable batched forwards. Across different benchmarks, \flowblock{} improves tokens per second (TPS) over LLaDA-2.1 and LLaDA-2.0, two serial block-wise dLLMs, by up to 2.95$\times$ and 4.01$\times$, while reducing latency by up to 53.6\% and 77.1\%, respectively. It also improves average accuracy by 1.3 points. Compared with D2F, a training-based inter-block-parallel baseline, \flowblock{} achieves higher accuracy and up to 16$\times$ higher batched serving throughput.
Daehoon Gwak, Minhyung Lee, Junwoo Park +1cs.LG cs.AI cs.CL
Diffusion large language models (dLLMs) offer a theoretical advantage in parallel generation over standard autoregressive models. However, parallel generation alone does not guarantee practical speedups. Realizing this efficiency requires specialized inference mechanisms, such as diffusion-aware caching and reuse. Consequently, as inference efficiency becomes a prerequisite for practical deployment, recent research has actively explored acceleration techniques across algorithms, architectures, and systems. However, rigorous comparisons remain difficult, as end-to-end latency stems from intricate trade-offs between algorithmic, architectural, and system-level factors that are often conflated in existing benchmarks. In this survey, we introduce a unified latency decomposition framework for dLLMs to disentangle these factors and analyze their impact on inference speed in real deployments. Guided by this framework, we categorize acceleration techniques along three axes covering algorithmic innovations, architectural and system optimizations, and inference-time scaling. Finally, we provide guidelines for reproducible benchmarking and highlight open challenges for realizing the full potential of parallel generation.
Multi-token prediction has been shown to increase data density during training, improve downstream text-generation quality, and serves as the defacto approach for self-speculative decoding. Existing foundation and open source models that use MTP heads commit to a static tree-based attention topology throughout the entire generation sequence, meaning the speculation depth, and thus the compute required during verification, stays constant regardless of the context. This is fundamentally misaligned with the entropy patterns of natural language where low-entropy regions often support reliable multi-step drafting, while high-entropy regions require more conservative speculation. To address this, we propose Entropy-guided Multi-Token Prediction (EntMTP), a training-free scheduler that toggles between tree-based attention topologies from a set of task-specific pareto-optimal trees conditioned on a running estimate of local generation entropy. By matching speculation depth to context predictability, EntMTP maximizes expected accepted-token throughput across the full distribution of generated text without sacrificing generation quality. When evaluated across Humaneval, ShareGPT, GSM8k, and Litbench benchmarks, EntMTP consistently achieves a 1.15x speedup against Hydra and peak speedup of 1.36x against Medusa baselines respectively.
Large language models (LLMs) are deployed for increasingly complex tasks involving planning and multi-step decision making, but high-quality performance on these tasks often requires generating long reasoning traces. This is a poor fit for latency-sensitive and interactive applications like voice assistants or coding agents, where generation latency can strongly affect user experience. Existing acceleration methods typically focus on token-level generation, without utilizing the structure of reasoning workflows. We introduce SSR: Self-Speculation for Reasoning Models, a training-free self-speculative decoding method that leverages the chain-of-thought (CoT) as a source of speculation. SSR uses the partial-CoT answer distribution as the drafter and the full-CoT distribution as the verifier, deriving both from the same model at different reasoning budgets. This builds on the observation that later partial-CoT responses often exhibit greater semantic and lexical overlap with the full-budget response. Due to this overlap, SSR can accept long draft prefixes at once, leading to large speedups on structured and long-form generation tasks. To further exploit draft-response overlap beyond the contiguous prefix accepted by standard speculative decoding, SSR also incorporates suffix decoding, using the draft to seed a suffix cache and recover useful spans beyond the accepted prefix, further reducing latency on tasks with high lexical overlap between the draft and the final response. We evaluate SSR on multiple structured and long-form generation tasks where it is most useful, and demonstrate a relative improvement of up to 24.1% on total generation latency for popular open-source models such as Qwen3.5 and Gemma-4.
Zhiwei Tang, Yuanyu He, Yizheng Han +4cs.LG cs.AI cs.CL
Autoregressive (AR) language modeling is the dominant paradigm for text generation, yet its sequential token-by-token decoding makes inference memory-bound and inefficient. Existing acceleration approaches, such as speculative decoding and diffusion language models, can yield speedups under certain conditions but do not directly address high-load batch serving--the scenario most critical for industrial-scale deployment. We introduce K-Forcing, a push-forward language modeling paradigm for joint next-k-token decoding. K-Forcing distills an existing AR model into a conditional push-forward mapping--one that transforms independent uniform noise variables into a joint sample of multiple future tokens in a single forward pass. This design preserves fixed-length outputs, reuses the AR teacher backbone, and remains compatible with standard AR serving infrastructure. We train this mapping via progressive self-forcing distillation, which gradually expands the prediction window while enabling the student to closely match the sequence distribution of the AR teacher. We evaluate K-Forcing on LM1B and OpenWebText using a standard causal Transformer backbone. When aggressively configured to generate k = 4 tokens per forward pass, K-Forcing delivers approximately 2.4-3.5x speedup across different batch sizes, while incurring modest quality degradation relative to its AR teacher. As inference increasingly dominates the lifetime compute cost of modern LLMs, K-Forcing offers a promising route toward accelerating AR generation under real-world high-load deployment.
Diffusion large language models (dLLMs) re-encode the entire prefix at every denoising step, causing recomputation that scales quadratically with context length and becomes prohibitive for long-context scenarios. We propose Prefilling-dLLM, a training-free prefill-decode disaggregation framework for dLLMs that partitions the prefix into N chunks, caches their KV representations once, and selects the top-K most relevant chunks with intra-chunk token sparsity for decoding, showing that sparse prefilling can outperform dense attention while reducing per-step complexity from quadratic in the full sequence length to quadratic only in the decode length. On LongBench and InfiniteBench, Prefilling-dLLM achieves state-of-the-art quality among dLLM acceleration methods, and an attention kernel that parallelizes decoding over the non-contiguously cached chunk KV yields 9.1--28.0x speedup at 8K--32K contexts. We further show that beginning-of-sequence tokens prepended to each chunk act as periodic attention anchors that eliminate the lost-in-the-middle phenomenon. Code is available at https://github.com/menik1126/Prefilling-dLLM.
Block-wise semi-autoregressive decoding is the standard inference paradigm for diffusion large language models (DLMs), but it imposes a strict dependency between blocks: the next block cannot begin until the current block is fully decoded or its denoising budget is exhausted. We observe that once a block exposes a reliable delimiter boundary or stable semantic prefix, continuation generation need not wait for every residual token to be resolved. We propose AsyncLane, a training-free decoding scheduler that decouples refinement from advancement. AsyncLane forks a generate lane at observed delimiter boundaries into a refine lane and a continuation generate lane: the prefix remains editable, while the continuation advances before prefix refinement finishes. The resulting lane tree records decoding dependencies and output order, while execution proceeds over the active lane set. To make this asynchronous schedule efficient under bidirectional attention, AsyncLane combines shared-prefix lane batching, lookahead draft reuse, cascading termination, and compact cache refresh with refresh-logit reuse, preventing model-call cost from scaling directly with the number of lanes. AsyncLane is a drop-in replacement for block-wise DLM samplers and requires no retraining. Experiments on mathematical reasoning and code generation show that AsyncLane consistently improves throughput while maintaining competitive quality. Across LLaDA and Dream backbones, AsyncLane achieves the highest TPS in all evaluated benchmark-length settings; relative to the fastest competing baseline, it reaches peak speedups of 2.95x on LLaDA and 3.04x on Dream, with especially large gains under longer generation budgets.
Speculative decoding accelerates generation by verifying multiple drafted tokens in a single target-model forward pass, reducing sequential decoding iterations. Model-free variants avoid auxiliary draft models by reusing text and model states already available during generation, but their speedup depends on the reliability of the constructed drafts. We identify two limitations of existing reuse-based methods: lexically anchored retrieval has limited recall under surface-form variation, and deterministic span copying can be brittle when the retrieved context does not uniquely determine the continuation. We propose \emph{AdaPLD}, a training-free method that adaptively improves both retrieval and draft construction. AdaPLD preserves high-precision lexical reuse while using semantic similarity to recover additional reuse opportunities when lexical matching fails. It further constructs branched reuse hypotheses to account for continuation uncertainty, rather than relying on a single copied span. Across diverse benchmarks, AdaPLD reduces target-model forward passes and achieves up to $3.10\times$ decoding speedup.
Diffusion large language models (DLLMs) enable non-autoregressive generation by iteratively denoising corrupted token sequences with bidirectional context. Despite their ability to update multiple positions in parallel, inference remains costly due to the many denoising steps required for high-quality generation. We propose SAID, a Scaffold-Aware Iterative Decoding framework that accelerates DLLMs by reallocating computation across tokens. SAID first spends denoising computation on scaffold tokens to establish the coarse semantic structure, and then completes predictable detail tokens with fewer steps. We further adapt SAID to block-wise diffusion decoding and introduce Confidence-Hierarchical Layered Generation (CHLG), which assigns additional steps only to low-confidence tokens. Experiments on LLaDA-8B and LLaDA 1.5 across math, coding, and knowledge benchmarks show that SAID significantly accelerates DLLM inference with a maximum speedup of 9.1x while maintaining competitive performance. Our code is publicly available: https://github.com/TH-AI-Lab-PKU/SAID.
Diffusion large language models promise parallel token generation, yet inference remains bottlenecked by deciding which masked tokens can be safely committed together. Fast-dLLM addressed this with KV caching and confidence-guided parallel decoding, but its decoding theory uses a homogeneous high-confidence assumption that effectively reduces each candidate set to its weakest selected token. We argue that this leaves speed on the table because real decoding steps exhibit heterogeneous confidence profiles. We propose \textbf{Fast-dLLM++}, a training-free extension that introduces \emph{Fréchet profile decoding}: selecting parallel commit sets from the full sorted confidence profile rather than a single worst-case confidence. The resulting rule is a heterogeneous-confidence generalization of Fast-dLLM's factor selector and it recovers the previous rule exactly in the equal-confidence case and adds a provable \emph{heterogeneity bonus} when the selected tokens have uneven confidences. Fast-dLLM++ leaves the model, diffusion process, and cache implementation entirely unchanged, making it a drop-in replacement for existing Fast-dLLM decoding. Experiments on GSM8K, MATH, HumanEval, and MBPP with the LLaDA-8B model show that the theoretical improvement translates directly into empirical gains: profile-aware selection improves the accuracy--throughput frontier by exploiting safe parallelism that weakest-token rules miss, achieving up to 37\% higher throughput at comparable accuracy. Our code release is at https://github.com/Ringo-Star/FastdLLM_plusplus.
Diffusion large language models (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) LLMs, offering faster inference through parallel or blockwise decoding. However, their masked language modeling formulation remains incompatible with standard token-level speculative decoding, one of the most effective acceleration techniques for AR models. In AR decoding, the causal mask preserves temporally valid token-level contexts, enabling a target model to verify multiple drafted tokens in a single forward pass. In contrast, dLLMs rely on mask tokens and bidirectional attention, causing the effective context to change across denoising steps and preventing direct token-level speculative verification. To bridge this gap, we propose a simple but effective speculative decoding algorithm for diffusion language models, named SimSD, which mainly adopts a plug-and-play masking strategy that equips dLLMs with temporally valid token-level contexts for speculative decoding. Our method explicitly introduces reference tokens from draft-model predictions and designs an attention mask that regulates their interaction with current-step tokens, allowing dLLMs to compute valid logits for drafted tokens in a single forward pass. This restores the key verification ability provided by causal masking in AR models while preserving the parallel decoding advantages of dLLMs. The proposed method is training-free and can be flexibly integrated with other acceleration techniques such as KV cache and blockwise decoding. Experiments on SDAR-family dLLMs across four benchmarks show that our method achieves up to 7.46x higher decoding throughput while maintaining and even improving average generation quality.
Speculative decoding accelerates LLM inference, but SOTA hidden-state-based drafters suffer from long-range decay: draft accuracy degrades as the speculative step increases. Existing work attributes this decay to train-inference mismatch and proposes test-time training (TTT) as a remedy, yet we observe that long-range decay persists even in TTT-trained drafters. We revisit long-range decay from the perspective of context information preservation. In hidden-state reuse, we argue the target hidden state acts as a biased context compression: it aggregates historical token information according to the attention query at the current position, yielding a compact representation optimized for immediate next-token prediction. This compression can suppress information less relevant to the current query but important for later speculative steps. In contrast, the target model's KV cache serves as an explicit context, retaining the complete set of token-wise KV representations. We therefore posit the KV-Reuse Hypothesis: allowing the draft model to reuse the target KV cache can provide richer signals for long-horizon drafting. To test this hypothesis, we introduce KVShot, a diagnostic framework that compares three reuse paradigms: hidden-only, KV-only, and hybrid. Extensive evaluations on Qwen3-8B show that KV-Reuse improves long-range acceptance, although end-to-end speedups remain marginal under current training pipelines. Our analysis identifies two key structural bottlenecks: shallow drafters struggle to estimate target queries accurately, and draft-side KV projections receive sparse gradient signals. These findings suggest that realizing the full potential of KV-aware decoding requires moving beyond TTT toward block-wise training paradigms. By exposing these bottlenecks, KVShot provides a foundational diagnostic testbed and a clear roadmap for designing next-generation inference architectures.
Some text generation tasks, such as Attribute Value Extraction (AVE), require decoding multiple independent sequences from the same document context. While standard autoregressive decoding is slow due to its sequential nature, the independence between output sequences offers an opportunity for parallelism. We present Hyper-Parallel Decoding, a novel decoding algorithm that accelerates offline decoding by leveraging both shared memory and computation across batches. HPD enables out-of-order token generation through position ID manipulation, significantly improving efficiency. Experiments on AVE show that attribute-value pairs are conditionally independent, enabling us to parallelize value generation within each prompt. By further stacking multiple documents within a single prompt, we can decode in parallel up to 96 tokens per prompt. HPD works with all LLMs, and reduces both inference costs and total inference time by up to 13.8X without compromising output quality, potentially saving hundreds of thousands of dollars on industry AVE tasks. Although designed for attribute extraction, HPD makes no assumptions unique to the AVE domain and can in theory be applied to other scenarios with independent output structures.