Speculative Decoding

Speculative decoding accelerates large language model inference without changing the target distribution, but no single drafting structure performs best across real-world workloads. Autoregressive multi-token prediction (MTP) is a lightweight, stable proposal mechanism, whereas block-parallel diffusion amortizes drafting latency over much longer candidate sequences; the better choice depends strongly on the output distribution. We present AngelSpec, a unified training framework for MTP and block-parallel speculative decoding that addresses this heterogeneity at three levels. At the training level, rather than fitting one universal drafter to a uniform data mixture, we co-specialize structure and data: the MTP drafter is trained on diverse conversational data for high-entropy open-ended chat, and the block-diffusion drafter on code and mathematics data for longer predictable continuations. At the architecture level, we propose DFly, 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. At the inference level, both acceptance length and verification cost vary with domain, request, online load, and hardware, so DFly treats verification as a shared batch-level resource: it reallocates compute toward high-confidence prefixes across requests and combines expected utility with a profiled cost model to adapt verification depth online. Across the Hy3 series, DFly raises the average accepted length on Hy3-A21B by roughly 30% and attains the highest average throughput at every tested concurrency from 4 to 64, a 1.98-2.40x speedup over autoregressive decoding and 10.5-11.8% higher throughput than DFlash. We release AngelSpec to support training and extending these methods.

Large language model agents often spend substantial wall-clock time waiting for tool call results. Tool-call speculation can hide this latency by predicting and pre-executing an agent's next tool call if the prediction matches the agent's eventual tool call, but existing speculators are typically separate draft models or cached traces that are poorly aligned with the deployed agent's own behavior. We identify this speculator-agent gap and show that the target agent itself is a strong next-call speculator. This points to a simpler design: unifying the agent and speculator within the same model. In this paper, we introduce the self-speculating agent, a single model that both solves tasks in agent mode and predicts its next tool call from partial trajectories in speculator mode, fully reusing prefix KV cache. To enable this dual-mode agent without degrading performance, we propose a joint agent-speculator reinforcement learning method, which derives speculation targets from the agent's own rollouts and alternates agent and speculator updates. Across agentic search QA and conversational tool-use agentic tasks, our method improves average next tool-call Hit@1 from 44.1 to 61.2 for Qwen3-4B and from 48.9 to 66.3 for Qwen3.5-4B, while preserving agent task success.

Specula is a push-button agentic system that generates high-quality formal specifications for large, complex system code and uses the specifications for highly effective model checking and bug finding. Specula employs large language model (LLM) based coding agents to autonomously develop TLA+ specifications, including invariants that describe correctness properties of the target system and formal models that describe the system implementation with the right level of abstractions. Specula is fully autonomous and thus eliminates the barrier of applying formal methods to real-world system code (as in traditional human-centric approaches). Meanwhile, Specula addresses limitations of LLM-driven techniques like reward hacking and hallucinations through self-evolving loops that iteratively improve specification quality by enabling the agents to deepen their understanding of system code and its behaviors. We have used Specula to check 48 open-source system projects; Specula found 249 bugs including many deep bugs that are hard to find by existing approaches. Specula has been used by several companies and is maintained at https://github.com/specula-org/Specula.

Large Mixture-of-Experts (MoE) language models are attractive for end-device deployment because only a small subset of experts is active per token, but their routed expert weights often exceed accelerator memory. We target latency-critical single-user settings where routed experts are staged on demand from CPU memory to a GPU or from Flash to a mobile NPU. In this setting, self-speculative decoding faces a new bottleneck: increasing the draft expert set improves accuracy but triggers extra expert loading, while cheap small-footprint drafts have low acceptance; moreover, verifying a multi-token block activates the union of target experts and is no longer close to one target step. We propose DraftExpert, an expansion-aware self-speculative decoding framework for expert-offloaded MoE inference. DraftExpert trains one lightweight accelerator-resident draft expert per layer by self-distilling residual, logit/token, and router-agreement signals from the frozen target MoE. At inference time, it uses a fixed-footprint shared+top-1+draft-expert drafter together with confidence--expansion truncation and target-expert prefetching, while final tokens are still exactly verified by the target model. On DeepSeek-V2-Lite and Moonlight-16B-A3B across CPU-GPU and Flash-NPU offload, DraftExpert improves decode throughput by 1.45x on average, raises draft acceptance to 8487%, and achieves 8688% prefetch hit rates.

Diffusion language models enable flexible arbitrary-order generation, but existing sampling methods are mostly designed for early masked diffusion models (MDMs). In this work, we study sampling for recent block diffusion language models (BDLMs). We show empirically and analytically that these models are naturally more aligned with left-to-right decoding than MDMs. Based on this observation, we propose Parallel Autoregressive Decoding (PARD), a simple training-free sampling method that preserves left-to-right unmasking structure while allowing parallel token commitment. Extensive experiments show that PARD consistently outperforms existing parallel samplers in generation quality, while achieving substantial speedups over pure AR decoding with only a small quality gap.

The increasing deployment of large language models (LLMs) has magnified the computational and memory bottlenecks of autoregressive decoding, where low compute intensity and bandwidth-bound kernels dominate inference cost. Weight pruning offers a promising remedy, but existing methods remain confined to either static pruning (SP), which permanently removes redundant weights but lacks adaptivity, or dynamic pruning (DP), which adapts to input sparsity but introduces runtime irregularity. This paper presents SPDP, a unified sparse-inference framework that integrates unstructured SP with input-adaptive DP for efficient LLM inference on GPUs. SPDP co-designs a new Tiled-Column-wise Bitmap Compressed (Tiled-CBC) format and two complementary GPU kernels: (1) a CUDA-core spMspV kernel featuring Hybrid Activation-aware Dynamic Shared-Memory Bitmap Decoding (HAD-SMBD) for fine-grained, runtime activation skipping, and (2) a Tensor-Core SpMM kernel optimized for prefill computation. This joint format-kernel design harmonizes static and dynamic sparsity, maintaining bandwidth-efficient memory access and high compute intensity under both phases of LLM inference. Comprehensive evaluations on inference-optimized GPUs demonstrate that SPDP achieves 1.24x-1.37x average speedup (up to 2.51x) over state-of-the-art sparse frameworks such as SpInfer, while matching perplexity with up to 25% higher sparsity. SPDP advances the inference efficiency-quality Pareto frontier, showing that unified static-dynamic pruning can deliver substantial throughput and performance-per-watt improvements in large-scale LLM serving.

Lossless acceleration schemes, such as speculative decoding, promise significant inference speedups by relying on dynamic token-level alignment between a draft and a target model. However, this guarantee of semantic equivalence masks a severe operational vulnerability: draft-target alignment can be systematically attacked. In this paper, we introduce ADSD, which, to the best of our knowledge, is the first prompt-suffix attack that collapses verifier acceptance by pushing draft probability mass toward tokens the target is unlikely to accept. ADSD uses Soft-Collapse, a verifier-aligned surrogate derived from the asymmetric speculative acceptance rule, together with a target-preservation objective that discourages obvious task corruption. ADSD successfully generates highly effective adversarial suffixes. On the GSM8K dataset, our attack increases the mean sample time by 62.3% while preserving the task quality. We further show that this vulnerability exists across different domains, speculative decoding strategies, and model architectures.

Speculative decoding accelerates autoregressive generation by having a cheap draft propose tokens that a target verifies in parallel. Frontier models increasingly ship a built-in Multi-Token-Prediction (MTP/NEXTN) draft head under the assumption that the draft is negligibly cheap. At million-token context this breaks: an MTP draft head typically runs full attention over the entire KV cache at every draft step, so its read grows linearly with context and comes to dominate the draft cost -- precisely where speculation is most valuable. The effect compounds with draft length (a deep native draft can turn net-negative, slower than no speculation) and sharpens under hybrid/linear-attention targets, where cheaper verification leaves the draft's full-attention read exposed. We apply a StreamingLLM-style sliding window plus attention sink to the draft's attention only (Windowed-MTP), leaving full-attention verification intact. It is training-free, drop-in, and lossless by construction: the full-attention target still decides every accepted token, so windowing changes only which tokens are proposed, never which are accepted. It bounds the draft's KV working set to a constant, dropping ~99% of KV entries at 1M. Across three architecture families (Qwen GDN-MoE 35B/122B and a Mamba2-hybrid NoPE 120B) at 1M context on a single GPU in SGLang, windowing cuts the per-decode-step cost over the shipping native MTP draft by +28% to +44%, an input-invariant margin that widens with context. Since per-token latency is this cost divided by acceptance length, at matched acceptance end-to-end decode latency improves by the same amount, and more where windowing also lifts acceptance, while preserving the target's verified output distribution. Finally, the unread draft KV -- 7.7-11% of total KV at 1M -- is reclaimed via a compact ring buffer at no acceptance or quality cost.

This work presents LeakyLMs, a set of attacks that leak proprietary model, architecture, and deployment information from production language models. LeakyLMs is the first to demonstrate that key model and deployment details can be inferred using only token generation timing, even when interacting through remote APIs. LeakyLMs introduces two core attacks. The first attack targets inference optimizations and deployment strategies. For example, our attack detects whether a provider uses speculative decoding, a widely deployed inference-time optimization, and further identifies the context length of the draft model used in the pipeline. Our measurements show that Google Gemini Flash 2.5 uses speculative decoding with a draft context window of approximately 128K tokens. The second attack recovers key architectural properties, including the number of transformer layers, hidden dimension size, and number of attention heads. To achieve this, LeakyLMs builds a detailed and accurate model of token-generation timing on modern NVIDIA GPUs, characterizing how latency scales with model configuration and hardware parameters. The attack then performs a search over the architecture space using this timing model. In experiments with Llama models, the near-correct architectural configuration appears in the top-10 guesses more than 90% of the time.

Diffusion language models (DLMs) can revise tokens bidirectionally, but standard decoding procedures often adapt them to left-to-right generation by producing text block by block. We study a simple plug-and-play inference pattern: first generate a complete draft, then refine the full response using bidirectional diffusion. Using LLaDA2.1-Flash and LLaDA2.1-Mini, we evaluate two configurations. In Flash-Flash, the same Flash model serves as both drafter and refiner, testing whether an existing model can improve its own block-autoregressive output through global refinement. In Mini-Flash, inspired by speculative decoding, we introduce speculative correction: Mini drafts a full response, and Flash revises it as an editable initialization. Flash-Flash improves GSM8K-384 accuracy from 0.848 to 0.899 while running 1.20 times faster than the selected Flash block-autoregressive baseline, and improves MBPP-384 from 0.545 to 0.693. Latency-window-matched Flash-only controls indicate that these gains persist after targeted tuning of block-autoregressive decoding. Causal ablations indicate that completed drafts provide useful initializations: refinement from a fully masked span performs poorly, full global refinement provides a clear additional gain on GSM8K, and local refinement captures much of the gain on MBPP and MATH. Mini-Flash provides useful quality-latency trade-offs, including MATH-384 performance of 0.294 versus 0.300 for Flash while running 2.17 times faster. These results support a Pareto-frontier interpretation rather than the claim that the heterogeneous cascade uniformly matches Flash quality. Overall, same-model draft-and-refine provides evidence that bidirectional refinement is a useful decoding primitive for DLMs, while speculative correction demonstrates a training-free route to fast DLM generation.

Speculative decoding, in which a lightweight draft model first generates a draft sequence that is then verified by the target model, has become a prevalent paradigm for accelerating large language model inference. Recent work such as DFlash further boosts drafting efficiency by leveraging diffusion drafters, whose parallel denoising mechanism enables draft generation in a single forward pass. In this work, we uncover a central pitfall of diffusion drafters: bidirectional attention is a double-edged sword. On one hand, it endows the model with parallel generation and global contextual modeling capabilities; on the other hand, this inherent global dependency introduces high variance at both the domain-level and the token-level: acceptance rates fluctuate substantially across different domains, and draft token quality also varies heterogeneously at different token positions. To tackle this issue, we propose AdaFlash framework, comprising two components: (i) an on-policy distillation (OPD) algorithm with reverse-KL divergence tailored for diffusion drafters, bringing stable convergence and effectively reducing domain-level variance; and (ii) an adaptive length head that dynamically adjusts the candidate sequence length on the fly, substantially lowering the verification cost of the target model and mitigating token-level variance. Experiments demonstrate that AdaFlash consistently improves speedup rate during deployment, with especially significant gains under high-concurrency, achieving up to 66% higher average throughput than previous SOTA. Our code is available at https://github.com/ZinYY/AdaFlash.

Long-horizon rollout generation has become the dominant systems bottleneck in agentic reinforcement learning (RL). As agents interact with environments over many turns, trajectories rapidly grow to tens of thousands of tokens, making synchronous RL training increasingly constrained by rollout. We propose WAR, a workload-aware rollout system that substantially accelerates synchronous agentic RL by jointly optimizing decoding and scheduling. WAR is built on a key observation: the optimal rollout optimization strategy depends on runtime load: (1) Under low load, WAR enables model-free speculative decoding with SuffixDecoding, which reuses suffix patterns from previously completed trajectories as speculative drafts for future rollouts. Unlike model-based drafters, SuffixDecoding introduces no additional draft model and avoids GPU contention with rollout generation. (2) Under high load, where saturated batched decoding leaves limited room for speculative speedup, WAR shifts the optimization focus to cache-aware scheduling. A global scheduler places requests across rollout replicas based on cache locality, trajectory progress and server load, reducing redundant KV-cache recomputation and mitigating load imbalance. By combining decoding-level suffix reuse with system-level rollout scheduling, WAR delivers robust throughput improvements across workload regimes without changing the underlying RL algorithm. WAR improves long-context agentic rollout throughput by 1.4x under low load and up to 1.6x under high load. These results show that WAR removes a major rollout bottleneck in synchronous agentic RL and provides a practical path toward scalable long-context agent training.

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 ($χ^2 = 162.5$, 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.

Masked diffusion language models (DLMs) enable parallel text generation by iteratively refining masked tokens, offering a promising alternative to autoregressive decoding. Recent lookahead-based decoding methods improve the accuracy--efficiency trade-off by exploring future decoding states before committing token updates. However, existing approaches mainly rely on shallow one-step lookahead, which optimizes immediate information gain but can be suboptimal for longer-horizon decoding trajectories. Meanwhile, we find that a naive extension for deeper lookahead is also ineffective, as fixed-depth rollout introduces additional computation and cannot adapt to heterogeneous intermediate decoding states. Thus, in this work, we propose AdaLook, an adaptive lookahead framework for DLM decoding. AdaLook dynamically determines whether to continue rollout based on candidate-score variance and further enables branch expansion when intermediate rollout states require additional exploration. This design avoids unnecessary deep rollout while allowing the decoder to re-trigger lookahead from informative intermediate states. Experiments on various benchmarks and models demonstrate that AdaLook achieves a better accuracy--decoding steps trade-off than existing one-step lookahead decoding methods.

Transformer reasoning is limited by autoregressive decoding, which repeat edly compresses rich hidden computation through token space and makes it difficult for intermediate reasoning states to persist across time. We in troduce Transformers with Temporal Middle-Layer Recurrence (T2MLR), a transformers-based latent reasoning architecture that fuses a cached middle layer representation from the previous token directly into an earlier layer of the current token position, enabling abstract intermediate computation to persist across decoding steps with little inference overhead. Across natural-language pretraining and multi-hop reasoning finetuning, T2MLR consistently outperforms data- and parameter-matched Transformer base lines. Moreover, applying recurrence to only a localized middle-layer block (as little as 20% of the network) often outperforms full-layer recurrence. Im portantly, T2MLR does not require pretraining from scratch: retrofitting the recurrent pathway into an existing pretrained 1.7B Transformer and briefly finetuning substantially improves math reasoning, lowering the barrier to practical adoption. These results suggest that effective latent reasoning in Transformers does not require looping over all layers as in previous works, but can instead emerge more strongly from targeted middle-layer recurrence.

Speculative decoding accelerates large language model (LLM) inference without compromising output quality. Recent parallel drafting methods further improve single-request performance by decoupling draft length from drafting latency, enabling longer drafts and higher mean accepted tokens (MAT). However, under high request concurrency, long drafts waste substantial computation on rejected tokens, increasing verification cost and potentially making speculative decoding slower than autoregressive decoding. We present D-Cut, an adaptive pruning method that selects draft tokens jointly across the batch and concentrates the verification budget on tokens most likely to be accepted. D-Cut is motivated by two observations. First, acceptance lengths vary considerably across concurrent requests; D-Cut therefore performs cross-request pruning, allocating the verification budget adaptively according to draft confidence. Second, verification cost depends strongly on the deployment environment, including GPU architecture and parallelism strategy; D-Cut incorporates a runtime cost model to adapt its pruning depth to the target environment. Experiments on dense and mixture-of-experts (MoE) models show that, under high concurrency, D-Cut improves the average speedup from $1.26\times$ to $1.65\times$, restores acceleration in dense-model configurations where long-draft baselines are slower than autoregressive decoding, and achieves up to $3.0\times$ speedup over autoregressive decoding on MoE models.

Sparse Mixture-of-Experts (MoE) models have become an important approach for scaling Large Language Models (LLMs), but their inference efficiency depends strongly on expert activation patterns. Speculative decoding (SD) accelerates autoregressive generation by verifying multiple draft tokens in parallel, yet existing draft selection strategies primarily optimize acceptance likelihood. In large-scale MoE models, however, selecting draft tokens also determines the union of experts activated during verification. We observe that confidence-driven SD can introduce \textit{expert scattering}: high-probability draft tokens may route to disjoint experts, increasing expert-weight memory traffic and reducing the speedup from speculation. Motivated by this observation, we revisit draft-tree selection under the non-uniform memory-cost structure of MoE inference. We propose \textsc{EcoSpec}, a cost-aware speculative decoding framework that incorporates predicted marginal expert activation cost into draft selection. With a lightweight expert predictor and a dynamic expert buffer, \textsc{EcoSpec} favors draft paths that preserve high acceptance likelihood while reusing experts already covered by the current verification set, without modifying the target-model verification rule. We evaluate \textsc{EcoSpec} on three large-scale MoE models, including DeepSeek-V3.1 (671B), Qwen3-235B-A22B, and GPT-OSS-120B, across reasoning, coding, question-answering, and dialogue benchmarks. \textsc{EcoSpec} consistently reduces active expert footprints and improves end-to-end decoding speed, achieving up to $1.62\times$ speedup. These results show that accounting for expert activation cost is important for efficient speculative decoding in large-scale MoE models.

Speculative decoding accelerates autoregressive language model inference by using a cheap drafter to propose multiple future tokens and a target model to verify them. A common design goal is therefore to improve draft quality while reducing auxiliary parameters and systems overhead. We study a negative result for this direction through PEFT-BD, a same-backbone speculative decoding method in which a LoRA-like adapter acts as a block-diffusion drafter for an autoregressive verifier. PEFT-BD is motivated by several attractive properties: it avoids tokenizer mismatch, avoids loading a separate draft model, adds only a small number of trainable parameters, and uses a BD3LM-style denoising objective to propose a block of tokens in parallel. Despite these advantages, PEFT-BD does not yield a practical speedup in our Qwen3-0.6B experiments. Although the method obtains nontrivial accepted prefixes, profiling shows that each speculative step requires an adapter-enabled full-backbone draft pass followed by an adapter-disabled full-backbone verification pass. Thus, the drafter is parameter-efficient but not compute-efficient. Our results isolate a simple but important condition for successful speculative decoding: the drafter must be substantially cheaper to execute than the verifier. Longer accepted prefixes alone cannot compensate when draft computation remains verifier-scale.

Speculative execution accelerates LLM agents by using a smaller, cheaper model to predict and pre-launch the next step while the environment is idle. However, existing speculators are stateless and discard all information between tasks, preventing prediction quality from improving with experience. We equip the speculator with three online memory systems that learn from past agent trajectories: a contrastive transition table tracking action-sequence statistics, an episodic memory retrieving contextually similar segments, and a confusion tracker suppressing recurring errors. We evaluate this approach on six benchmarks spanning three speculation types: action prediction, observation prediction, and chained prediction. Memory-augmented speculation yields a 19--39% relative accuracy improvement on action prediction and up to a $2.5\times$ increase on observation prediction tasks with repetitive action spaces. These gains grow continuously as memory accumulates and generalize across speculator models of varying cost. All speculation is lossless because it runs during idle time at zero added wall-clock cost, and the actor's trajectory is identical to non-speculative execution.

Speculative decoding accelerates autoregressive generation by letting a lightweight drafter propose multiple tokens that are verified by a larger target model. Although effective for text-only LLMs, speculative decoding yields limited gains in VLMs because drafters often diverge on vision-critical content, while existing multimodal acceleration methods do not directly address irrelevant visual evidence or optimize the verifier-accepted prefix length that governs speedup. We propose TIGER, a Text-conditioned vIsual GatEd Routing framework for multimodal speculative decoding. TIGER dynamically selects a sparse set of context-relevant visual tokens based on the drafter's current textual state, rather than expose the full visual token set or a fixed compressed interface. To better align training with inference-time efficiency, we optimize the drafter with acceptance-aligned group-based policy training using verifier-derived rewards based on accepted prefix length, built on top of distillation warm start with KL anchoring. This encourages the drafter not only to imitate the target model, but also to produce speculative continuations that survive verification for longer prefixes. Experiments show that TIGER yields consistent gains in accepted prefix length and speculative speedup under exact verifier-side speculative decoding, while achieving favorable quality-latency trade-offs with comparable downstream accuracy in visual-routing analyses.

Speculative decoding has significantly accelerated Large Language Model (LLM) inference by alleviating memory-bound bottlenecks. However, traditional speculative decoding typically relies on auxiliary draft modules, incurring significant training and communication overhead. Although recent methods attempt to generate drafts within the target model itself, they often fail to fully exploit its latent parallel capacity due to a lack of structural coordination. In this paper, we propose \textbf{Progressive Tree Drafting (PTD)}, which employs a structured, guided parallel drafting strategy to harness the model's parallel potential. By coupling a progressive tree structure with a stepwise pruning mechanism, PTD actively guides the LLM to explore multiple semantic paths in a single forward pass, ensuring both draft diversity and coherence. Experiments demonstrate that PTD achieves up to $2\times$ decoding speedup across various benchmarks while remaining training-free and model-agnostic. Our code is available at: https://github.com/MINE-USTC/PTD.

Neural networks can learn algorithmic input-output mappings, but trusting a learned executor requires more than a correct final answer because the state transitions that produce it are usually hidden. To make those transitions visible, we introduce a trace-supervised symbolic neural CPU, a factorized learned execution architecture that combines recurrent control, an explicit operation router over a fixed differentiable arithmetic-logic unit bank, destination-masked register writeback, complete trajectory supervision and matched fixed-point replay. The model exposes the selected operation, source and destination registers, register trajectory, memory signals and writeback semantics at every step. On the principal 16-wide benchmark, the non-quantized executor reproduces reference execution exactly, while the eight-bit quantization-simulated executor preserves the symbolic operation path through programs of 1,000 instructions. When the same execution is evaluated against a matched fixed-point replay, the residual numerical drift disappears, showing that it comes from a mismatch between continuous and low-precision reference semantics rather than from execution failure. We compare recurrent, Transformer, temporal-convolution, temporal graph-inspired and state-space controllers, and the ablations show that operation-gate supervision is necessary for an inspectable execution path. Hidden-opcode memory-pressure tasks expose the remaining limits in delayed state use and temporal binding. We also extend the interface with ValueMemory, hybrid adaptive leaky integrate-and-fire controllers, candidate-constrained symbolic control trained through behaviour cloning and actor-critic reinforcement learning, and an RV32I base-integer semantic bridge. Together, these results establish a trace-verifiable framework for interpretable, low-precision and controllable neural execution.

Speculative decoding accelerates sampling from an autoregressive LLM by using a faster auxiliary model to draft tokens which are then verified in parallel by the LLM. Standard speculative decoding is lossless: its rejection and resampling steps exactly preserve the LLM's sampling distribution. Recent work argues that relaxing this strict guarantee can yield further speed-ups, controlled capability-speed trade-offs, or even capability gains. We practically investigate training-free relaxed speculative decoding techniques, unify existing approaches within a shared framework, benchmark them on contemporary settings, and distil takeaways and empirical findings for practitioners. Important takeaways include: relaxation can require considerable capability evaluation unlike lossless speculative decoding, and many relaxed approaches rely on a drafter that is a good language model, making them unsuited for lightweight dedicated multi-token-prediction drafters.

Speculative decoding accelerates LLM inference by drafting several tokens and verifying them in parallel. Block-diffusion drafters such as DFlash produce a draft block in one pass but model only per-position marginals, and best-first tree methods such as DDTree expand candidate trees from those marginals. The released Domino drafter adds a GRU-based causal correction that makes each draft token distribution path-dependent, a structure DDTree's factorized formulation cannot represent. We introduce DominoTree, a training-free best-first draft tree scored by Domino's conditional, non-factorized correction along each root-to-node path, made practical by restricting the per-node correction to a candidate top-M set. On Qwen3-4B across eight benchmarks, DominoTree reaches up to 6.6x speedup over autoregressive decoding and the highest mean accepted length of any evaluated method, up to 10.7 tokens per round, at every tested temperature. DominoTree constructs its tree with a GPU-native CUDA-graph builder that is bit-identical to a reference Python implementation, so acceptance is unchanged, while keeping per-round tree construction cheap. With this builder as default, DominoTree improves throughput over the released Domino decoder, the drafter it builds on, at every tested temperature: 9% to 10% overall on Qwen3-4B and up to 22% on Alpaca. It also outperforms DDTree and CaDDTree at every tested temperature, not only under greedy decoding. On Qwen3-8B, DominoTree keeps the highest accepted length at every temperature and gives a 24% throughput gain over DDTree at T=0; at higher temperature its edge over DDTree and CaDDTree narrows to a tie and a small loss, while its aggregate gains over DFlash and Domino persist.

Despite the rapid advancements of large language models (LLMs), LLM serving systems remain memory-intensive and costly. The key-value (KV) cache, which stores KV tensors during autoregressive decoding, is crucial for enabling low-latency, high-throughput LLM inference serving. In this survey, we focus on system-aware KV infrastructure for serving LLMs (abbreviated as sKis). We revisit recent work from a system behavior perspective, organizing existing efforts into three dimensions: execution and scheduling (temporal), placement and migration (spatial), and representation and retention (structural). Furthermore, we analyze cross-behavior co-design affinity and behavior-objective links, highlighting future opportunities. Our work systematizes a rapidly evolving area, providing a foundation for understanding and innovating KV cache designs in modern LLM serving infrastructure.

Speculative decoding accelerates LLM inference by drafting multiple tokens and verifying them in parallel. Block-parallel drafters such as DFlash further improve drafting efficiency by predicting an entire block in one pass, but their position-wise predictions lack explicit intra-block causal conditioning. Recent methods such as Domino and DSpark attempt to introduce such causality into block-parallel drafting, but they require training the draft model from scratch, which limits their flexibility and increases training cost. We propose DeLS-Spec, a decoupled long-short context speculative decoding method. DeLS-Spec treats the fixed DFlash model as a long-context expert and introduces a lightweight local head as a short-context expert. The local head can be trained independently with a standard next-token prediction objective, without joint training with the target model or the DFlash backbone, leading to extremely low training cost. At inference time, DeLS-Spec combines long-context and short-context logits, and the local head is not tied to a specific DFlash checkpoint, making the method more modular and flexible. Experiments on Qwen3 models show that DeLS-Spec consistently improves speedup and average acceptance length over DFlash across math, code, and dialogue benchmarks.

Speech large language models (Speech LLMs) typically encode speech into sequences far longer than text, creating a major efficiency bottleneck during autoregressive decoding. A common remedy is to compress the speech sequence at the adapter level to remove temporal redundancy before it enters the LLM; however, such early downsampling risks discarding fine-grained information that cannot be recovered. We propose SpeechKV, which applies a learned pooling to the KV cache of speech tokens inside the LLM. This design allows the LLM to fuse speech and text internally while directly accelerating decoding. Trained on 71K hours of speech data, SpeechKV compresses the speech to approximately text-level granularity yet maintains performance on par with or even slightly better than the uncompressed baseline, with relative gains of 6.6% on out-of-domain entity recognition and 2.3% on OpenASR, while delivering at least 1.49 times decoding speedup that scales with audio length.

Speculative decoding greatly increases the interactivity of autoregressive language models by trading off computation for extra tokens generated in a single forward pass. Factorized draft models are especially efficient because they predict future-token marginals in parallel, but their independence assumption causes acceptance rates to degrade sharply as the speculative budget grows. We analyze this limitation and introduce Weaver, a lightweight autoregressive adapter that constructs proposal trees from the top-K marginals of a factorized drafter. Weaver restores conditional dependencies between proposed tokens while avoiding a full-vocabulary projection. To support fast verification for models with Gated Delta Net layers, we derive a rollback-free tree-verification algorithm and implement optimized CUDA kernels in SGLang. By combining these model and systems contributions we achieve a 4.37-fold speedup over autoregressive decoding, and outperform a highly optimized DFlash baseline by 24.7%.

We introduce Nemotron-Labs-Diffusion, a tri-mode language model (LM) that unifies AR, diffusion, and self-speculation decoding within a single architecture. Trained with a joint AR-diffusion objective, Nemotron-Labs-Diffusion can switch modes to sustain high throughput across deployment settings and concurrency levels. Our study shows that (1) AR and diffusion objectives are complementary: diffusion improves lookahead planning, while AR provides left-to-right linguistic priors. (2) In self-speculation mode, diffusion drafts while AR verifies, outperforming multi-token prediction (MTP) methods in both acceptance rate and real-device efficiency. (3) A speed-of-light analysis further demonstrates diffusion's long-term potential, with up to 76.5% more tokens per forward pass than self-speculation under an optimal sampler. Scaling to 3B, 8B, and 14B parameters, our Nemotron-Labs-Diffusion family, including base, instruct, and vision-language models, consistently outperforms state-of-the-art open-source AR and diffusion LMs in both accuracy and speed. For example, Nemotron-Labs-Diffusion-8B decodes 6x more tokens per forward than Qwen3-8B with comparable accuracy, translating to 4x higher throughput on SPEED-Bench with SGLang on a GB200 GPU.

Speculative decoding accelerates Large Language Model (LLM) inference by decoupling draft generation from target verification. While recent parallel drafters efficiently propose long token sequences in a single forward pass, they suffer from rapid acceptance decay due to a lack of inter-token dependencies. Furthermore, indiscriminately verifying these extended blocks wastes critical batch capacity on tokens with high rejection risks, severely degrading throughput in high-concurrency serving systems. We introduce DSpark, a speculative decoding framework that unifies high-throughput parallel generation with adaptive, load-aware verification. To maintain draft quality, DSpark utilizes a semi-autoregressive architecture, coupling a parallel backbone with a lightweight sequential module, to introduce intra-block dependency modeling and mitigate suffix decay. To optimize system efficiency, DSpark employs confidence-scheduled verification, dynamically tailoring the verification length for each request based on estimated prefix survival probabilities and engine-specific throughput profiles. On offline benchmarks across diverse domains, DSpark substantially improves the accepted length over state-of-the-art autoregressive and parallel drafters. When deployed within the DeepSeek-V4 serving system under live user traffic, DSpark successfully mitigates verification waste. Compared to the established production baseline (MTP-1), DSpark accelerates per-user generation speeds by 60 to 85 percent at matched throughput levels. More importantly, by preventing severe throughput degradation under strict interactivity constraints, it enables performance tiers that were previously unattainable, shifting the Pareto frontier of our serving system.

Key-value (KV) cache growth is a major bottleneck in autoregressive decoding, as memory and bandwidth scale linearly with context length. Existing KV eviction methods often rely on static heuristics or proxy scores, which poorly track future token utility and cause brittle eviction as relevance shifts. To address this, we introduce KVpop, which learns a fixed-budget KV eviction policy by directly supervising the keep-or-drop decision. The scorer is trained against a novel future-attention target, computed efficiently without materializing dense attention maps. We further introduce a delayed memory-based scorer that, uniquely among learned eviction methods, defers scoring for a fixed number of steps to exploit near-future context. On AIME and HMMT mathematical reasoning, KVpop retains 98% of full-attention performance on Qwen3-4B at 75% KV cache compression and 97% at 88% compression, consistently outperforming established eviction baselines. Qwen3-8B shows even stronger results, reaching near-full teacher performance. These results show that supervising eviction with future-attention signals cuts memory costs while maintaining quality.

Large language models (LLMs) generate fluent outputs that can be wrong. Unlike humans, who often exhibit cues when providing false information, LLMs produce errors that are difficult to detect because autoregressive decoding provides no mechanism for verifying intermediate reasoning before state progression. We introduce Heaviside Continuity of Rolling Coefficients (HCRC), a verification-first execution framework that reformulates inference as predicate-gated state transitions governed by a Heaviside Gate. HCRC combines model confidence with independent verification signals from a parallel worker architecture, allowing execution to advance only when predefined correctness predicates are satisfied. This prevents invalid intermediate states from propagating, reducing epistemic entropy without modifying the underlying model. We evaluate HCRC on software-engineering and reasoning tasks across thirteen proposers from four providers. On capable proposers, the gate reduces the false-completion rate (FCR) from 4--7% to 0% while remaining latency-competitive and, in some settings, faster than the unwrapped model. On weaker proposers, it converts false completions into honest halts instead of corrupting downstream state. Beyond benchmarking, HCRC has operated for months as the production control plane of an agentic coding environment, authorizing file mutations, verification-driven progress reporting, and memory compaction. These results establish HCRC as a general framework for verification-driven LLM execution, showing that reliable reasoning can be achieved through principled execution control rather than model scale alone.

This report describes our approach to the Efficient Qwen Competition, where the goal is to enable low-latency serving of Qwen3.5-4B on a resource-constrained NVIDIA A10G GPU. Our system combines a quantized target model with speculative decoding. To recover accuracy, we apply quantization-aware distillation to the target model while retaining the original quantization grid. To speed up decoding, a block-diffusion drafter specialized for the quantized target model is trained using a two-stage procedure: first learning from the high-precision target and then adapting to the low-precision target. Because the drafter is invoked at every speculative decoding step, we further reduce its overhead with quantization and sliding-window attention, preserving draft-token acceptance while improving long-context decoding latency. As a result, our submission achieves a 6.978$\times$ average speedup over the baseline while satisfying the required quality thresholds, ranking 3rd overall. We hope these results provide useful insights for practical LLM inference. The code and resources are available at https://github.com/nota-github/adaptfm-quant-dflash

With the rise of small quantized GGUF-based language models and their increasing use for on-device inference tasks, we have seen the growing need for an approach capable of reliably delivering these models at scale even under severe memory bandwidth constraints such as those imposed by pure CPU implementations. Fixed-depth speculative decoding has emerged as one promising technique, but in practice, it often leads to performance degradation due to either bandwidth saturation, instability, or even catastrophic resource exhaustion resulting in system failure. To overcome this problem, we introduce AdaptiveSD, a fully runtime-adaptive speculative decoding framework aimed at ensuring robust, reliable execution across the spectrum of model types and workloads. Our solution consists of four tightly-coupled components working together in a continuous feedback loop: a Runtime Monitoring Engine tracking multiple signals relevant to ongoing computation, an Adaptive Draft Controller enforcing an eleven rule policy hierarchy prioritizing system resource preservation over raw draft count, a Dynamic Policy Engine employing a suite of heuristic and reinforcement learning techniques to dynamically modify policies depending upon workload behavior, and finally, a KV Cache Coordination Layer managing cache states with fine-grained control through INT8 shadow buffers and position aware evictions. While conventional approaches focus solely on maximizing throughput, we instead assess the effectiveness of our approach based on several key metrics including wasted drafted compute and inter-token latency dispersion alongside standard measures of speculative efficiency.

LLM agents are becoming a common interface for research, coding, and question answering, yet their Thought-Action-Observation loop is often serial: the model reasons, emits a tool call, then idles the GPU until the result returns. This wait consumes 16-37% of wall time in our workloads and 35-61% in prior reports. Speculative tool execution can hide this wait, but existing systems need auxiliary predictors, historical traces, or static workflow graphs, leaving a gap for training-free, day-one deployment. We observe that the model can be its own predictor: a probe forked at the start of generation predicts Qwen3-32B's upcoming tool name with 74.6-99.6% accuracy across five benchmarks. We present SPORK (Self-sPeculative fORKing), a training-free controller that dispatches the speculated tool call early, overlapping its execution with the remaining chain-of-thought decode. A cost model captures when speculation breaks even, and each component improves one of its terms: a prefix-cache fork cuts probe cost, a confidence gate filters mispredictions, and partial-token accept turns rejected probes into speculative-decoding drafts. On acceptance, the tool result is ready when reasoning ends; on rejection, SPORK falls back to serial execution with no correctness penalty. On real-tool benchmarks, SPORK cuts Qwen3-32B's GAIA P95 by 18% (131.9 to 108.1 s); the mechanism holds across model sizes from 4B to 32B and across dense and mixture-of-experts models, with task accuracy within 1 pp of baseline or better wherever measured. SPORK deploys as a thin controller over standard completion APIs (no retraining, no auxiliary models, no offline traces) and is orthogonal to token-level speculative decoding. SPORK is open source at https://github.com/baihuajun24/spork.

Thinking has emerged as a critical capability for Large Language Models (LLMs) tackling complex tasks. However, its reactive nature, where reasoning is passively triggered only upon receiving a user response, inevitably introduces latency that compromises conversational fluidity. This stands in sharp contrast to human dialogue, where speakers proactively anticipate and plan future content during natural pauses to ensure seamless interaction. To bridge this gap, we propose Proactive Thinking, a framework that empowers models to pre-compute potential response elements during conversational downtime instead of waiting idly for the next input. We then introduce a training-free baseline that can think ahead by anticipating future states, balancing efficiency and quality through speculative continual thinking. To evaluate this approach in practice, we adapt three benchmarks of varying complexity into time-aware environments that simulate real-time conversational flow. We demonstrate that proactive thinking effectively improves interaction efficiency without compromising performance. Ultimately, this work advocates for a fundamental shift toward more intelligent, anticipatory, and real-time conversational AI.

Dense video captioning aims to generate temporally grounded descriptions of video events, benefiting both event-level video understanding and generation. In this domain, autoregressive video large language models have emerged as a prevalent paradigm due to their strong generative and cross-modal modeling capacity. However, generating dense captions under the token-by-token paradigm severely limits inference efficiency and hinders scalability as video length and event density increase. In this work, we propose a parallelized autoregressive framework that not only improves generation efficiency but also enhances temporally grounded captioning performance. Our key insight is to exploit the weak local dependencies across temporally distinct events to restructure the causal dependency graph, thereby enabling lossless parallel generation. Specifically, tokens with weak cross-event dependencies can be decoded in parallel, while tightly coupled tokens within each event retain sequential decoding to preserve local semantic coherence. To realize this insight, we introduce two key components for lossless parallel decoding: (1) a latent global planning mechanism that automatically learns the event-level structure and produces compact tokens encoding global inter-event causality while adaptively aggregating event-level audio-visual semantics, guiding subsequent dependency restructuring and parallel decoding; and (2) an event-factorized parallel decoding mechanism that effectively balances local focus with global inter-event awareness. Experiments on various benchmarks demonstrate the clear advantage of our approach in both efficiency and performance in omni-modal event grounding and captioning. Project website: https://github.com/showlab/PadCaptioner.

Low-bit quantization shrinks language models but treats precision as a single global hyper-parameter: every weight uses the same bit-width. We introduce Variable Bit-width Quantization (VBQ), a training-time method in which each contiguous group of 64 weights learns its own resolution from {1,2,4,8} bits via a Gumbel-Softmax relaxation, trained jointly by an alternating optimization that gives the precision logits a clean, task-aligned signal. VBQ discovers a consistent, strongly heterogeneous allocation within individual projection types, not merely across layers, impossible to express with per-layer methods: 69% of groups collapse to 1 bit, the LM head averages 1.09 bits, while the first MLP block keeps ~2.5 bits. This pattern is stable enough to freeze into a fixed recipe and reuse without further search. The recipe yields a "bigger-but-smaller" regime: a 131M model at 1.82 mean bits reaches perplexity 4.2 on TinyStories, beating a 55M FP16 model (PPL 4.4) at 3.8x less storage, and lets a 1.46B model on FineWeb-Edu match a 593M FP16 control at ~3.7x less storage with 2.5x more parameters. As quality-per-byte, VBQ is 3.9-8.4x more efficient than FP16. The recipe maps directly to packed low-bit storage, so it also accelerates inference: with custom fused dequantize-and-multiply kernels, memory-bandwidth-bound autoregressive decode is faster at equal output, and the speedup grows with scale (parity at 131M, 1.9x at 1.0B, 4.7x at 9B on Apple silicon). A distributional analysis (KL divergence and argmax-flip rate) reveals a striking mechanism: deeper layers progressively self-heal the quantization error injected by early layers. The win is a from-scratch, train-time phenomenon; scaling the search economically beyond 1.5B parameters remains open. VBQ reframes precision as a learnable, non-uniform resource and shows that spending a fixed bit budget unevenly beats spending it uniformly.

Speculative decoding accelerates autoregressive generation by drafting a block of tokens that the target model verifies left-to-right, committing only the longest accepted prefix. Block (DLM-style) drafters predict the whole block in parallel, which is fast but trained with a full-block cross-entropy that supervises every position against the gold continuation -- even though inference discards every token after the first rejection. Recent acceptance-aware objectives patch this by reweighting the full-block loss; we instead use teacher-forced learning as a motivation for how supervision should concentrate on the accepted prefix. A mask-only block drafter has no input-side channel for gold-prefix conditioning, so AUF approximates that prefix-sensitive supervision on the loss side by keeping the cross-entropy support only through the drafter's first predicted failure. AUF is a single, detached change to the CE support -- no auxiliary objective, no verifier rollouts, and no change to the inference pipeline or the exactness contract. Within fixed drafter backbones and serving settings on Qwen3-8B, AUF raises the DFlash drafter's average emitted length $τ$, averaged over six benchmarks, from 2.40 to 2.61, with a gain on every benchmark, and transfers to Domino's two-branch head (2.56 to 2.68). Two findings sharpen the picture: the decay-only baseline reaches higher token accuracy on the shared block mask yet decodes worse, and on DFlash, once AUF truncates the support, the standard exponential position-decay weighting becomes empirically inert.

Large Language Models (LLMs) are increasingly deployed as autonomous financial agents initialized with explicit behavioral mandates such as "preserve capital" or "avoid speculative bets" that are meant to govern every decision throughout deployment. In practice, however, as market context accumulates over long horizons, these mandates gradually lose their behavioral influence, a phenomenon we formalize as Mandate Salience Decay (MSD). To measure MSD objectively, we introduce FinPersona-Bench, a simulation benchmark in which a synthetic market decouples observable price from hidden fundamental value, enabling falsifiable evaluation across three failure modes: trading without signal in calm markets, panic-selling during crashes, and ignoring fundamental value during speculative bubbles. Evaluating 18 leading frontier and open-source LLMs, each assigned one of three behavioral profiles ranging from strict capital preservation to aggressive growth, shows that MSD compounds over time and is model-dependent. In crash scenarios, the behavioral gap between static agents and those receiving periodic mandate re-grounding grows 4.4x from the first to the final quarter of the simulation. The effects of mandate re-grounding are not uniformly positive: it consistently helps conservative agents in low-signal markets but actively worsens behavior for aggressive agents in the same setting. These findings suggest that reliable long-horizon deployment requires selective, mandate-aware re-grounding based on agent profile and market regime.

Speculative decoding accelerates inference by using a lightweight draft model to generate candidate tokens in parallel, and are then verified by the target model, enabling lossless acceleration. Recently, diffusion-based speculative decoding further improves parallelism by generating multiple tokens per forward pass via block-level diffusion, achieving state-of-the-art (SOTA) performance. However, existing methods adopt a fixed inference block size and assume a uniform optimal decoding strategy across all inputs. In this paper, we show that this assumption is suboptimal, as the optimal block size varies across samples and plays a critical role in speculative decoding performance. Moreover, these values exhibit a clear local structure, concentrating around the training block size, which reduces the problem to a low-dimensional and structured decision space. Based on these insights, we propose BlockPilot, a sample-adaptive policy that predicts the optimal block size from the prefilling representation. Specifically, we formulate block size selection as a lightweight policy learning problem and propose an instance-adaptive decision mechanism that predicts the optimal block size based on the representation of the prefilling stage. The prediction is performed only once after prefilling, allowing for seamless integration. Extensive experiments demonstrate that our method is plug-and-play, introduces minimal overhead, and consistently improves efficiency, achieving an acceptance length of 5.92 and a 4.20$\times$ speedup on Qwen3-4B under temperature $T=1$.

Modern Vision-Language-Action (VLA) planners for autonomous driving emit a chain-of-causation (CoC) reasoning step \emph{before} producing a trajectory. The reasoning is autoregressive and dominates inference latency, while the trajectory head is parallel and cheap. Latency is an operational constraint in autonomous driving, so accelerating the reasoning step is the central problem we address. We observe that CoC reasoning has two qualitatively different needs: most tokens continue routine setup that follows naturally from the ego-trajectory history, and a small fraction encode commitments that require fresh visual evidence about an unexpected situation. We split this reasoning into two specialized paths: a \emph{routine reasoner} that handles the predictable continuation by attending to trajectory history, and a \emph{deliberative reasoner} (the unmodified VLA target) that handles novel cases by attending to current visual evidence, using the speculative decoding framework as the architectural template for how the two paths cooperate. Unlike standard speculative decoding, our routine reasoner is not a smaller replica of the target; the two reasoners are deliberately specialized to read different parts of the prompt. We propose two techniques to realize this. First, we introduce \textbf{FlatRoPE}, a 1D rotary positional embedding in the draft that breaks the rotational symmetry of the target's 3D M-RoPE, redirecting attention away from visual tokens and onto trajectory-history tokens. Second, we introduce \textbf{Action-aware RL (AARL)}, a post-training stage that uses an action-quality reward together with a static-reference KL anchor. Together, our two-reasoner system reduces the reasoning-step running time by approximately $4\times$ relative to the original Alpamayo planner.

Hard-constrained sequential decision systems have no certified way to spend the test-time compute of modern AI: executing the multi-step drafts of a learned policy or a frozen LLM forfeits the feasibility guarantee a trusted solver provides, while invoking the solver at every step forfeits the speed the AI offers. Certificate-Gated Prefix Acceptance (CGPA) closes this gap with a certified speculative-execution contract for untrusted AI agents: a trusted verifier rejects constraint-violating transitions exactly, a conformally calibrated value boundary gates the longest low-cost prefix within a per-segment regret budget, and the rest defers to the solver, so safety, regret, and speed decouple by construction. The contract drives every untrusted proposal source - adversarial drafters and six heterogeneous frozen LLMs (including a 12B model that violates constraints in 98% of direct rollouts) - to zero applied violations; a certificate-aware learned boundary, conformally calibrated, drives mean regret three orders of magnitude below unguarded acceptance, to within sampling noise of the stepwise oracle (95% CI spanning zero), and under calendar shift a learned proposal source overtakes it on 15 of 18 held-out days. On a deployment-scale unit-commitment instance it turns a frozen 8B LLM into a 2.96x per-episode wall-clock speedup at 2.1% regret, outpacing the domain heuristic (1.79x) and a safe receding-horizon baseline (1.07x): the more capable the untrusted source, the faster the certified system, at guarantees that never change.

Speculative decoding accelerates language model inference by using a fast drafter to propose candidate tokens that are then verified by a larger target model. Existing theory largely studies the stochastic, distribution-preserving setting, where the goal is to exactly sample from the target distribution. In contrast, many practical systems use greedy decoding, relaxed acceptance rules, or tree-based candidate sets, where success is governed by local ranking and threshold events rather than exact distributional equality. We develop a theory for these regimes. We identify that many common acceptance criteria have rejection regions that can be characterized as lower level sets of the target distribution. For these, we characterize the exact KL divergence required for rejection yielding exact certificates and sharp margin-based bounds for strict greedy decoding, additive and multiplicative relaxed acceptance, top-(m) relaxed criteria, and entropy-thresholded acceptance. We then extend the framework to greedy tree decoding, deriving exact and margin-only certificates for when the target greedy token remains covered by the drafter's top-(m) candidates. Finally, we evaluate the resulting certificates on Qwen3 models, showing that relaxed and tree-based criteria substantially enlarge the region of certified acceptance, especially on decoding steps with low target model distribution margin. These results complement existing distribution-preserving analyses of speculative decoding by characterizing the deterministic local acceptance events common in practical inference systems.

Spec-Driven Development (SDD) frameworks guide Large Language Model (LLM)-powered code generation through formal specifications, yet they differ fundamentally in how they enforce traceability between requirements and generated code. This paper presents two controlled empirical studies comparing three SDD frameworks: $traceSDD$, which enforces mandatory per-line requirement citations using hierarchical REQ-XXX.Y.Z identifiers; $Spec Kit$, which uses artifact-level traceability through user stories and acceptance criteria; and $OpenSpec$, which relies on post-hoc external trace maps. We measure two primary outcomes across two frontier LLMs -- Claude Sonnet 4.6 (N=20, 4 conditions, 240 implementations) and GLM-5-turbo (N=50, 4 conditions, 600 implementations): $output$ $determinism$ (lexical similarity across independent LLM sessions) and $automated$ $hallucination$ $detection$ $rate$ (TDR). Our pre-registered analysis reveals a consistent, cross-model replicated trade-off: the uncited condition produces significantly higher determinism than the cited condition (Claude: $d=-0.76$, $p=0.003$; GLM: $d=-0.72$, $p<0.001$), while only the cited condition enables automated hallucination detection (TDR: Claude 86.4%, GLM 88.0%, vs 0% for all alternatives, FPR=0% across both studies). traceSDD (cited) significantly outperforms $Spec Kit$ on determinism (Claude: $d=0.47$, $p=0.049$; GLM: $d=0.42$, $p=0.003$) but not OpenSpec (Claude: $d=0.18$, $p=0.44$; GLM: $d=0.14$, $p=0.32$). These findings establish that citation annotations trade determinism for verifiability, and that this trade-off generalizes across model architectures.

A stateless inference server (vLLM, SGLang, TensorRT-LLM) idles between requests while the accelerator waits; a stateful session reclaims that idle time. Speculative pre-positioning decodes the session forward to its next decision point with the target model's own forward pass and no draft model, moving the cross-request prefill and entry-decode off the critical path: the next request resumes from a pre-paid entry on its delta, or, when a confidence gate fires, is answered from a cached distribution in one near-constant vocabulary scan with no decode, at a cost only of energy and a rare, bounded false accept. The payoff is conditional on capability: a capable model fires the gate at near-full coverage and about 87% precision (a smaller one never clears it), returning the first token in about 1.0 ms versus the 39 ms decode a prefix cache still pays.

Speculative decoding (SD) has emerged as a key solution to accelerate the inference of autoregressive models. However, in the field of image generation, it faces the challenge of low acceptance rates, and directly relaxing its criteria leads to degradation in image quality. In this paper, we propose a novel content-aware speculative decoding algorithm, termed CSD, which integrates an entropy-based probability relaxation mechanism with an optimal resampling strategy to enhance the inference efficiency for autoregressive image generation. By leveraging the informational uncertainty inherent in different regions of an image, CSD dynamically adjusts the acceptance probability of candidate tokens, increasing the acceptance rate in low-detail areas to accelerate generation. Moreover, a distribution alignment filter is introduced to ensure the output distribution to be aligned with the target model, which significantly improves the generative quality. Experiments conducted on Lumina-mGPT and Janus-Pro demonstrate that the superiority of the proposed CSD. Our source code is available at https://github.com/aderfebr/CSD.

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.

AI coding agents dramatically accelerate implementation speed but introduce two structural failure modes that existing spec-driven approaches do not fully solve: (1) context explosion -- the agent must reason over an entire repository at once, degrading output quality as the context window fills; and (2) silent spec-code drift -- code evolves, the specification does not, and the divergence becomes invisible until it is costly to repair. We present the Spec Growth Engine, a lightweight framework that addresses both failure modes through a machine-readable spec graph whose nodes carry explicit contract/design separation, a Spine context assembler that scopes agent context to an ownership path, a vertical-slice growth protocol that enforces hardest-first ordering, and a drift gate that makes spec-code divergence a blocking merge condition. The design synthesises well-established software engineering principles (Parnas information hiding, C4, ADRs, Walking Skeleton, Reflexion Models, Fitness Functions) into a lean, code-coupled, machine-enforced whole -- without the overhead of heavy-weight frameworks such as RUP or MDA.

We present HyperDFlash, a block-parallel speculative decoding framework tailored to DeepSeek-V4's Hyper-Connections (HC). Despite the strong performance of DeepSeek-V4's native Multi-Token Prediction (MTP) module on initial token drafting, its draft accuracy degrades sharply at later positions, as error accumulation from unverified intermediate tokens harms draft acceptance rates. Although the original DFlash method supports efficient one-pass block drafting, it cannot be seamlessly adapted to the HC paradigm, since DeepSeek-V4's multi-path residual stream induces inherent feature misalignment with conventional drafting designs. To resolve this architectural mismatch, we propose two dedicated, model-aligned optimizations for HC residual streams. First, we adopt pre-collapse residual states as the exclusive conditioning signal, preserving complete multi-path structural information and better aligning the drafter with the target's native prediction pathway. Second, we replace the heavy generic linear compressor with a lightweight gated residual reducer, whose parameters are directly inherited from the target model's built-in hc_head module. This design yields input-aware path aggregation with three orders of magnitude fewer parameters while maintaining precise architectural alignment. We further enhance model training via a targeted KL distillation loss applied to the LM-head, regularizing predictions against the target distribution to improve early draft quality. Extensive experiments across math reasoning, code synthesis, and conversational benchmarks demonstrate that HyperDFlash consistently outperforms both the native MTP baseline and vanilla DFlash adaptation, achieving substantial gains in average accepted draft length and decoding speedup. These results validate HC alignment, gated reduction, and targeted distillation for high-performance speculative decoding.

Interleaved multimodal reasoning improves visual grounding by revisiting visual evidence during multi-step generation, yet existing methods typically rely on token replay, repeatedly forwarding selected visual tokens. A natural shortcut is to reuse the historical visual key-value (KV) cache directly. However, we identify a critical failure mode of this strategy: cached visual keys are already bound to their original positional context. Such stale positional binding distorts attention under later decoding contexts and can trigger severe autoregressive decoding collapse. This failure suggests that effective cache reuse requires reconstructing visual evidence under positions compatible with the current decoding state, rather than directly copying position-bound historical cache entries. To this end, we propose Position Rebinding Cache Reuse (PRCR), a cache-level framework for replay-free visual revisiting. PRCR stores raw visual KV cache together with their original spatial coordinates, then reassigns position-compatible coordinates to select entries and rebinds their keys before injecting the reconstructed cache into the active decoder cache. This design reuses historical visual evidence while preserving textual positional continuity and relative visual structure. Experiments across multiple multimodal reasoning benchmarks show that PRCR achieves replay-level or better performance, improving average accuracy by 5 percent and reducing visual-revisiting computation by up to tens of thousands of times.

Speculative decoding accelerates inference by letting a draft model propose tokens for a target model to verify, raising a concrete safety question: at temperature zero, can draft-side behavior leak into safety-scored outputs? We answer with Typical-Acceptance Invariance Screen (TAIS), a behavioral-equivalence screen that pairs target-only and speculative outputs on the same safety battery and requires byte-identity evidence, TOST equivalence at +/-3pp, and per-task Cohen's h below a calibrated null cutoff of |h| < 0.1. Applied to a 16,783-sample confirmatory core plus 44,066 matched expansion samples (fp16/bf16 execution, canonical and DPO-adversarial drafts, GPTQ-4bit drafts, two seeds, and four safety benchmarks), the tested temperature-zero vLLM stacks show no detectable safety divergence under TAIS. The largest absolute Cohen's h on matched target-only versus speculative refusal is 0.024, roughly an order of magnitude below the conventional trivial-effect floor; 25 of 27 per-task TOST contrasts pass at the +/-3pp margin (the two non-pass contrasts are capability-domain Wald-CI edge cases at identical ceiling rates, not genuine non-equivalence); the DPO-adversarial draft produces byte-identical output to the canonical draft across 4,006 samples; and bf16 changes 36%-53% of output bytes without moving any per-task safety rate outside equivalence. A separate 4,006-sample 70B production-scale probe, which lacks a matched 70B target-only arm and is therefore not counted as a TAIS pass, produces AdvBench refusal 0.839 over 700 AdvBench completions with 95% Wilson CI [0.809, 0.864]. We make no claim about sampling temperatures, untested frameworks, untested model families, or tree-speculation variants such as EAGLE and Medusa.

While speculative decoding improves inference throughput for multi-batch long-context Large Language Models (LLMs), its efficiency is often limited by a verification bottleneck where Key-Value (KV) cache loading dominates latency. Existing compression methods fail in this regime: static eviction incurs accuracy loss due to saliency shift, while dynamic selection introduces prohibitive computational overhead during the verification path. We propose Dustin, a sparse verification framework designed for long-context speculative decoding. Dustin integrates lookahead signals from the draft model with historical attention from the target model to identify critical tokens with high fidelity across multi-step verification windows. To reduce recomputation latency, this approach further employs a sparse estimation scheme that restricts importance scoring to a minimal subset of attention heads. Evaluations on PG-19 and LongBench with Qwen2.5-72B demonstrate that Dustin achieves a 27.85x speedup in self-attention and a 9.17x end-to-end decoding speedup at a 32k sequence length, all with negligible accuracy degradation.

Masked diffusion language models decode by iteratively unmasking tokens, where the unmasking order defines an "order of thought" that strongly influences generation quality yet is typically chosen heuristically. We derive a tractable upper bound on the sequential decoding mismatch, measured by the Kullback-Leibler divergence and expressed in terms of the model's pathwise log-likelihood, with tightness under sufficient model expressivity. This bound induces a dense self-aware reward over ordered trajectories, casting order selection as a principled policy optimization problem with a frozen denoiser. We instantiate this idea as Self-Aware Scheduling (SAS), which learns a lightweight order policy using Group Relative Policy Optimization and applies seamlessly to both any-order and semi-autoregressive decoding. On Sudoku with 1B MDM, SAS improves puzzle accuracy from 82.0% (best heuristic schedule) to 91.8%, and reaches 97.5% with second-stage fine-tuning along learned trajectories. On mathematical reasoning with LLaDA-8B, SAS improves pass@1 on GSM8K from 64% to 76% and on MBPP from 39.5% to 41%, consistently matching or exceeding heuristic schedules across generation lengths and block sizes. Project page: https://jimmyxu123.github.io/SAS

We present RLM-Cascade, a proxy-layer system that applies speculative decoding at the response level to reduce LLM API costs without requiring model architecture access or a shared vocabulary. A fast, inexpensive draft model generates a candidate response; a capable verify model accepts, enhances, or is bypassed entirely depending on a lightweight complexity router. On a real-world agentic coding workload (Claude Code), RLM-Cascade achieves a draft-use rate of 88.8% across 125 production requests, reducing API cost by 45.8% relative to a direct Opus baseline. Counter-intuitively, the proxy also reduces end-to-end latency: median response time is 2,026 ms versus 3,698 ms for Native Opus -- a 1.83X speedup at p50 -- because the SKIPPED path (DeepSeek only, no Opus call) dominates the workload distribution. Quality matches or exceeds the Opus baseline: 100% pass rate on a 20-task Code/Math/Instruct benchmark versus 95% for Native Opus. We further describe a rule-based complexity router that selects the SKIPPED path for simple agentic turns and a hybrid tool-call strategy that bypasses the speculative pipeline for schema-critical tool-selection turns. RLM-Cascade is deployed in production as an enterprise AI infrastructure component and published as open source with a live metrics dashboard and Prometheus endpoint.

Autoregressive models excel in visual generation by treating images as 1D sequences of discrete tokens, mirroring language modeling. However, this flattening discards the intrinsic 2D spatial locality of visual signals, creating severe computational bottlenecks during inference. We introduce Spatially Speculative Decoding (SSD), a framework that aligns the predictive objective with the natural geometry of images. Rather than predicting only the immediate next token in a 1D sequence, our model simultaneously predicts the adjacent horizontal token and the token directly below it. By capitalizing on this 2D spatial correlation, spatially speculative decoding overcomes the memory wall in visual inference. Our approach accelerates autoregressive image generation by up to 13.3x while maintaining high fidelity on DPG-Bench and GenEval. Our results suggest that respecting the underlying geometry of vision unlocks massive computational efficiencies, paving the way for real-time, high-resolution autoregressive generative models.

Speculative inference accelerates large language model (LLM) decoding but provides no inherent safety guarantees. Existing safety defenses are largely incompatible with speculative inference: they either introduce additional computation or disrupt the draft-verify mechanism, negating acceleration benefits. This reveals a fundamental incompatibility between current safety methods and speculative decoding. We propose SafeSpec, a safety-aware speculative inference framework that integrates risk estimation directly into the verification process. SafeSpec attaches a lightweight latent safety head to the target model to jointly evaluate semantic validity and safety in a single forward pass. When unsafe generations are detected, SafeSpec applies rollback and safety-guided reflective multi-sampling to recover safe continuations rather than terminating generation. We model jailbreak attacks as distributional shifts over generative trajectories, where adversarial prompts increase the probability of harmful continuations without eliminating safe ones. Under this model, SafeSpec performs risk-aware trajectory recovery within the speculative decoding process. Across multiple models and adversarial benchmarks, SafeSpec achieves a substantially improved safety-efficiency trade-off. On Qwen3-32B, SafeSpec reduces attack success rates by 15% while preserving a 2.06x inference speedup on benign workloads, demonstrating that speculative acceleration and inference-time safety can be jointly optimized.

Reinforcement learning (RL) has become a representative post-training paradigm for LLMs, enabling strong reasoning and agentic capabilities. However, rollout generation remains a dominant latency bottleneck because autoregressive sampling decodes responses sequentially and a small number of long-tailed generations often determine completion time. Speculative decoding (SD) offers a natural way to address this bottleneck, as it is a well-established technique for serving fixed LLMs that reduces latency by rapidly drafting tokens and accepting them through parallel verification while preserving the target-model distribution. However, its practical speedups do not directly carry over to RL rollouts: (i) the evolving target policy makes any fixed drafter increasingly mismatched with the policy's output distribution; and (ii) active batch sizes shrink throughout rollout decoding, shifting decoding from compute-bound to memory-bound regimes where parallel verification can exploit underutilized compute. Therefore, accelerating RL rollouts requires both a drafter that remains effective under long, high-temperature generations from an evolving policy and system-aware use of SD that avoids compute-bound regimes. We present EfficientRollout, a system-aware self-SD framework designed to address this gap for RL rollouts. EfficientRollout induces a quantized drafter from the target model (i.e. self-speculative decoding), keeping it coupled to the evolving policy without separate drafter pretraining or online adaptation. It further coordinates a system-aware SD toggle policy with acceptance-aware draft-length adaptation, enabling speculation only in beneficial regimes while matching the drafting budget to evolving drafter quality. EfficientRollout reduces rollout and end-to-end latency by up to 19.6% and 12.7%, respectively, over an accelerated AR rollout baseline, while preserving final model quality.

Speculative decoding (SD) accelerates autoregressive Large Language Models (LLMs) by drafting multiple tokens and verifying them in parallel, but it faces a scaling limitation: increasing the draft budget improves speed only when acceptance remains high and drafting overhead stays low. This ceiling has been difficult to break because prior head-based SD methods face a causality-efficiency dilemma. Autoregressive drafters produce path-conditioned candidates that are effective for tree speculative decoding with higher acceptance length, but their drafting cost grows with tree depth. Bidirectional block-diffusion drafters generate all positions in one pass, but their branch-agnostic marginals can form individually plausible yet mutually inconsistent trees, wasting budget and reducing acceptance. We propose JetSpec, a head-based SD framework that combines one-forward drafting efficiency with branch-wise causal conditioning. JetSpec trains a causal parallel draft head over fused hidden states from the frozen target model, producing candidate trees whose scores align with the target model's autoregressive factorization. This enables JetSpec to convert larger draft budgets into longer accepted prefixes and higher end-to-end speedup. Across math, coding, and chat benchmarks on dense and MoE Qwen3 models, JetSpec consistently outperforms bidirectional-head and tree-based SD baselines. On H100 GPUs, JetSpec achieves up to 9.64x speedup on MATH-500 and 4.58x on open-ended conversational workloads, with further latency gains demonstrated through vLLM integration under realistic serving loads. Our code and models are available at https://github.com/hao-ai-lab/JetSpec.