LLM Inference Acceleration

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

108 papers in the last four weeks, up 120% on the four weeks before. 1.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 677

Apr 20, 2026cs.CL

DeInfer: Efficient Parallel Inferencing for Decomposed Large Language Models

Existing works on large language model (LLM) decomposition mainly focus on improving performance on downstream tasks, but they ignore the poor parallel inference performance when trying to scale up the model size. To mitigate this important performance issue, this paper introduces DeInfer, a high-performance inference system dedicated to parallel inference of decomposed LLMs. It consists of multiple optimizations to maximize performance and be compatible with state-of-the-art optimization techniques. Extensive experiments are carried out to evaluate DeInfer's performance, where the results demonstrate its superiority, suggesting it can greatly facilitate the parallel inference of decomposed LLMs.

You-Liang Huang, Xinhao Huang, Chengxi Liao +1

Boston University · Boston, Massachusetts, USA · HKUST (Guangzhou) +2

LLM Inference LLM Inference Acceleration

Apr 19, 2026cs.AR

Predictive Multi-Tier Memory Management for KV Cache in Large-Scale GPU Inference

Key-value (KV) cache memory management is the primary bottleneck limiting throughput and cost-efficiency in large-scale GPU inference serving. Current systems suffer from three compounding inefficiencies: (1) the absence of unified KV cache sizing across all attention architectures--particularly multi-head latent attention (MLA), which is unsupported in general-purpose frameworks, resulting in up to 57x memory over-provisioning; (2) confinement of KV cache to a single memory tier (GPU HBM) despite the availability of a rich hierarchy spanning CPU DRAM, CXL-attached memory, NVMe via GPUDirect Storage, RDMA fabric, and parallel filesystems; and (3) reactive eviction policies that discard reusable state, forcing redundant recomputation. We present a unified system that addresses all three problems. Our architecture-variant-aware sizing engine computes exact memory requirements per attention type, enabling up to 7.4x higher batch sizes. A six-tier memory hierarchy extends effective KV cache capacity from 40 GB to over 38 TB per node while maintaining sub-millisecond time-to-first-token (TTFT) for hot entries. A Bayesian reuse predictor with Beta conjugate priors over 16 (block-type, transition-type) pairs achieves 70-84% cache hit rates, combined with EMA-scored head-granular eviction and RoPE-aware prefetching. Component-level validation on trace replay using ShareGPT, LMSYS-Chat-1M, and agentic workloads demonstrates 70-84% cache hit rates. Analytical projections combining validated component behavior with published hardware specifications indicate 1.4-2.1x projected TTFT reduction, 1.7-2.9x throughput improvement, and 47% cost reduction compared to state-of-the-art baselines.

Sanjeev Rao Ganjihal

Independent Researcher

KV-Cache Offloading KV Caching KV-Cache Eviction KV-Cache Management LLM Inference Acceleration KV-Cache Reuse

Apr 19, 2026cs.AI

Hive: A Multi-Agent Infrastructure for Algorithm- and Task-Level Scaling

Large language models are increasingly deployed as complex agentic systems that scale with task complexity. While prior work has extensively explored model- and system-level scaling, algorithm- and task-level scaling remain largely unaddressed, constraining the full potential of agentic systems. At the algorithm level, allocating additional inference-time computation can enhance workflow capacity but introduces cross-path redundancy: overlapping computations across multiple reasoning branches. At the task level, complex tasks can be decomposed into subproblems and delegated across multiple agents for improved scalability and parallelism. However, existing infrastructures' scheduling is unaware of the existence of multiple agents, missing opportunities to optimize resource allocation. We propose Hive, a multi-agent infrastructure that enables algorithm- and task-level scaling. Hive features a description frontend that captures per-agent behavior and supports test-time scaling algorithms. Leveraging this specification, our backend introduces two key mechanisms: Logits Cache that reuses intermediate logits across redundant sampling paths to mitigate cross-path redundancy at the algorithm level, and Agent-Aware Scheduling that efficiently allocates compute and KV-cache resources according to agent contributions at the task level. Experiments show that Logits Cache achieves an average speedup of

1.11\times

-

1.76\times

for re-sampling, and Agent-Aware Scheduling reduces the hotspot miss rate by

33\%

-

51\%

.

Zizhang Luo, Yuhao Luo, Youwei Xiao +3

Peking University Beijing, China

LLM Inference Efficiency Multi-Agent LLM Systems Multi-Agent System Optimization Inference-Time Scaling LLM Inference Acceleration Multi-Agent Systems

Apr 19, 2026cs.CL

CRISP: Compressing Redundancy in Chain-of-Thought via Intrinsic Saliency Pruning

Long Chain-of-Thought (CoT) reasoning is pivotal for the success of recent reasoning models but suffers from high computational overhead and latency. While prior works attempt to compress CoT via external compressor, they often fail to align with the model's internal reasoning dynamics, resulting in the loss of critical logical steps. This paper presents \textbf{C}ompressing \textbf{R}edundancy in Chain-of-Thought via \textbf{I}ntrinsic \textbf{S}aliency \textbf{P}runing (\textbf{CRISP}), a framework that compresses CoT by exploiting the model's intrinsic saliency. Our analysis reveals a distinct phenomenon: the reasoning termination token \texttt{[object Object]} acts as an information anchor, where its attention pattern effectively demarcates essential reasoning from redundancy. Based on this finding, we design a policy that utilizes these intrinsic attention signals to guide atomic compression operations. In contrast to coarse-grained pruning strategies, CRISP strategically distills the reasoning chain to maximize information density while preserving logical coherence. Empirical results across various backbone models and mathematical datasets demonstrate that CRISP achieves a 50-60% reduction in token count without compromising accuracy, effectively mitigating the efficiency bottleneck of long-context reasoning. We open-source our implementation to facilitate further research in efficient reasoning.

Yangsong Lan, Hongliang Dai, Piji Li

College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing, China · The Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education, Nanjing, China.

LLM Pruning LLM Compression LLM Inference Acceleration CoT Compression

Apr 19, 2026cs.CL

Probabilistic Programs of Thought

LLMs are widely used for code generation and mathematical reasoning tasks where they are required to generate structured output. They either need to reason about code, generate code for a given specification, or reason using programs of thought. The typical approach to code generation is to prompt the model and generate samples until an appropriate program is obtained. Within this process, sampling

n

programs from the language model requires

n

GPU compute-intensive generations which becomes prohibitively expensive for larger values of

n

. In this work, we address this limitation by exposing the LLM's distribution within the generated programs themselves. We propose a novel test-time framework we dub probabilistic programs of thought to obtain more samples from the model with fewer LLM generations. Given a program generated by a model and the associated next-token probabilities, we build a probabilistic program that compactly represents exponentially many deterministic programs. Since performing probabilistic reasoning in this probabilistic program is much cheaper, our approach allows sampling new programs without any additional GPU compute and little CPU overhead. We instantiate our approach on benchmarks for code generation, code understanding and mathematical reasoning and report improvements in performance with fewer generations from the LLM.

Poorva Garg, Renato Lui Geh, Daniel Israel +3

University of California Los Angeles · Allen Institute for AI

LLM-Based Program Synthesis Efficient Language Model Reasoning LLM Inference Acceleration Mathematical Reasoning Probabilistic Programming LLM Reasoning

Apr 19, 2026cs.DC

UCCL-Zip: Lossless Compression Supercharged GPU Communication

The rapid growth of large language models (LLMs) has made GPU communication a critical bottleneck. While prior work reduces communication volume via quantization or lossy compression, these approaches introduce numerical errors that can degrade convergence, accuracy, and stability. We present UCCL-Zip, a unified design that integrates lossless compression directly into GPU communication primitives. UCCL-Zip supports both point-to-point (P2P) and collective communication without modifying user-facing APIs or compromising numerical correctness. For P2P communication, Uzip-P2P employs a split-send pipeline that exposes transmissible data early and overlaps compression with communication, while preserving high GPU efficiency by operating on large data blocks. For collective communication, Uzip-NCCL integrates compression into NCCL's persistent kernel model via fused execution, eliminating redundant memory traffic and kernel launches. In real workloads, UCCL-Zip accelerates RL weight synchronization by up to 47.5% and reduces vLLM end-to-end inference latency by up to 10%, all without application changes.

Shuang Ma, Chon Lam Lao, Zhiying Xu +8

UC Davis · Harvard University · Amazon Web Services +1

GPU Kernel Optimization GPU Acceleration Communication-Efficient Distributed Training LLM Inference Acceleration

Apr 18, 2026cs.LG

Open-TQ-Metal: Fused Compressed-Domain Attention for Long-Context LLM Inference on Apple Silicon

We present Open-TQ-Metal, the first implementation of fused compressed-domain attention on Apple Silicon, enabling 128K-context inference for Llama 3.1 70B on a single 64GB consumer Mac -- a configuration impossible with all existing inference frameworks. Open-TQ-Metal quantizes the KV cache to int4 on the fly and computes attention directly on the compressed representation via custom Metal compute shaders, eliminating all intermediate dequantization matrices. Across 330 experiments spanning two model families (Gemma 4 31B and Llama 3.1 70B), the fused sdpa_int4 kernel achieves 48x attention speedup at 128K context over the dequantize-then-attend baseline, reduces KV cache memory from 40 GB to 12.5 GB (3.2x compression), and maintains identical top-1 token predictions to FP16 inference. We further provide the first cross-architecture analysis of KV cache quantization methods, revealing that the attention scale factor -- not model size -- determines whether angular quantization schemes like PolarQuant succeed or fail, with Gemma 4's attn_scale=1.0 amplifying directional error 25-100x more than Llama's standard 1/sqrt(d) scaling.

Sai Vegasena

Ensue

AI Accelerator Inference Self-Attention Long-Context Language Model Inference LLM Inference Acceleration Efficient Attention Attention Quantization+2

Apr 18, 2026cs.AI

Step-GRPO: Internalizing Dynamic Early Exit for Efficient Reasoning

Large reasoning models that use long chain-of-thought excel at problem-solving yet waste compute on redundant checks. Curbing this overthinking is hard: training-time length penalties can cripple ability, while inference-time early-exit adds system overhead. To bridge this gap, we propose Step-GRPO, a novel post-training framework that internalizes dynamic early-exit capabilities directly into the model. Step-GRPO shifts the optimization objective from raw tokens to semantic steps by utilizing linguistic markers to structure reasoning. We introduce a Dynamic Truncated Rollout mechanism that exposes the model to concise high-confidence trajectories during exploration, synergized with a Step-Aware Relative Reward that dynamically penalizes redundancy based on group-level baselines. Extensive experiments across three model sizes on diverse benchmarks demonstrate that Step-GRPO achieves a superior accuracy-efficiency trade-off. On Qwen3-8B, our method reduces token consumption by 32.0% compared to the vanilla model while avoiding the accuracy degradation observed in traditional length-penalty methods.

Benteng Chen, Weida Wang, Shufei Zhang +2

East China Normal University · Shanghai AI Laboratory · Fudan University +1

RL for Language Model Reasoning LLM Inference Acceleration Early-Exit Neural Networks Large Reasoning Models

Apr 18, 2026cs.LG

SinkRouter: Sink-Aware Routing for Efficient Long-Context Decoding in Large Language and Multimodal Models

In long-context decoding for LLMs and LMMs, attention becomes increasingly memory-bound because each decoding step must load a large amount of KV-cache data from GPU memory. Existing acceleration strategies often trade efficiency for accuracy by relying on heuristic pruning that may discard useful information. At a deeper level, they also tend to indiscriminately preserve all high-scoring tokens, treat early tokens as indispensable anchors, or rely on heuristic head routing, reflecting an insufficient mechanistic understanding of the attention sink phenomenon. In this paper, we show that the attention sink phenomenon corresponds to a stable, reachable, and error-controllable fixed point constructed during training. Based on this insight, we propose SinkRouter, a training-free selective routing framework that detects the sink signal and skips computations that would otherwise produce near-zero output. To translate this mechanism into real-world acceleration, we develop a hardware-aware Triton kernel with block-level branching and Split-K parallelism. We conduct extensive evaluations on a diverse suite of long-context benchmarks, including LongBench, InfiniteBench, CVBench, MileBench, and MMVP, using both text-only and multimodal backbones such as Llama-3.1-8B, Llama-3.1-70B, Yi-9B-200K, LLaVA-1.5-7B, and LLaVA-1.5-13B. Across these settings, SinkRouter consistently improves decoding efficiency while maintaining competitive accuracy, and reaches 2.03x speedup with a 512K context.

Junnan Liu, Xinyan Liu, Peifeng Gao +4

Harbin Institute of Technology (Weihai) · University of Hong Kong, Hong Kong, China · City University of Hong Kong, Hong Kong, China

GPU Acceleration Self-Attention Long-Context Language Model Inference Efficient VLM Inference LLM Inference Acceleration Attention Sinks+1

Apr 17, 2026cs.CL

Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning

Parallel reasoning enhances Large Reasoning Models (LRMs) but incurs prohibitive costs due to futile paths caused by early errors. To mitigate this, path pruning at the prefix level is essential, yet existing research remains fragmented without a standardized framework. In this work, we propose the first systematic taxonomy of path pruning, categorizing methods by their signal source (internal vs. external) and learnability (learnable vs. non-learnable). This classification reveals the unexplored potential of learnable internal methods, motivating our proposal of STOP (Super TOken for Pruning). Extensive evaluations across LRMs ranging from 1.5B to 20B parameters demonstrate that STOP achieves superior effectiveness and efficiency compared to existing baselines. Furthermore, we rigorously validate the scalability of STOP under varying compute budgets - for instance, boosting GPT-OSS-20B accuracy on AIME25 from 84% to nearly 90% under fixed compute budgets. Finally, we distill our findings into formalized empirical guidelines to facilitate optimal real-world deployment. Code, data and models are available at https://bijiaxihh.github.io/STOP

Jiaxi Bi, Tongxu Luo, Wenyu Du +2

The Chinese University of Hong Kong, Shenzhen · Shenzhen Loop Area Institute · DualityRL

LLM Inference Acceleration Large Reasoning Models

Apr 17, 2026cs.LG

Sparse Prefix Caching for Hybrid and Recurrent LLM Serving

Prefix caching is a key latency optimization for autoregressive LLM serving, yet existing systems assume dense per-token key/value reuse. State-space models change the structure of the problem: a recurrent layer can resume from a single stored state rather than requiring the entire token history. This asymmetry opens a new design point between no reuse and dense caching: store exact recurrent states at a sparse set of checkpoint positions and, on a cache hit, resume from the deepest stored checkpoint and recompute the remaining suffix exactly. We formalize sparse prefix caching as checkpoint placement under a distribution over overlap depths, yielding an exact O(NM) dynamic program. For use cases where requests share a non-trivial prefix (e.g. asking different questions about a single long document), we show that our method consistently improves the Pareto frontier traced by standard heuristics on real-world data. Across QuALITY and System Prompts, distribution-aware placement dominates every fixed-budget baseline on the measured layer-group Pareto frontier and matches or outperforms the strongest heuristic (block caching) while typically using substantially fewer checkpoints, with the largest gains at low checkpoint budgets where the overlap distribution is most non-uniform. The method is most relevant when many requests share a substantial but not identical prefix within a retained cache entry. It preserves exact outputs, does not change the recurrent computation itself or require new recurrent update kernels, applies to recurrent/SSM layers whose hidden state can be extracted and restored exactly, and for hybrid models can be combined with existing KV-cache compression techniques.

Mikhail Shirokikh, Sergey Nikolenko

LLM Serving KV-Cache Management LLM Inference Acceleration Prefix Caching

Apr 17, 2026cs.CL

EvoSpec: Evolving Speculative Decoding via Real-Time Vocabulary and Parameter Adaptation

Speculative decoding accelerates Large Language Model inference via a draft-then-verify paradigm, yet the output projection layer becomes a bottleneck as vocabulary sizes scale. While existing static pruning methods effectively reduce this overhead, they suffer from precipitous drops in acceptance rate in specialized domains or topic-switching scenarios due to their inability to capture dynamic distribution shifts. To address this, we introduce EvoSpec, a framework that enables real-time evolution of the draft model through dynamic vocabulary and parameter adaptation. Unlike static or purely retrieval-based approaches, EvoSpec employs a context-aware mechanism that retrieves critical long-tail tokens via efficient semantic and statistical indexing. Furthermore, we propose a lightweight online alignment strategy utilizing curriculum learning to continually minimize the distributional gap between the draft and target models. Extensive evaluations across specialized domains (coding, law, and medicine) confirm that EvoSpec overcomes the limitations of static baselines. On EAGLE-3, it achieves a 1.13x speedup in these settings over the state-of-the-art static baseline FR-Spec, with 27% lower memory overhead than standard online adaptation.

Shuyu Zhang, Lingfeng Pan, Qicheng Wang +6

School of Computer Science and Technology Xidian University Xi’an, China

Speculative Decoding LLM Inference Acceleration

Apr 17, 2026cs.LG

Faster LLM Inference via Sequential Monte Carlo

Speculative decoding (SD) accelerates language model inference by drafting tokens from a cheap proposal model and verifying them against an expensive target model via rejection sampling. Because rejection truncates the draft block at the first error, throughput degrades when draft and target diverge. Rather than rejecting draft tokens outright, we propose to reweight them. To this end, we introduce sequential Monte Carlo speculative decoding (SMC-SD), which replaces token-level rejection with importance-weighted resampling over a population of draft particles. SMC-SD is a principled approximate inference scheme that trades exactness for additional speed, while preserving theoretical bounds on its per-step approximation error. Because LLM inference is memory bandwidth-bound, the arithmetic needed to draft particles and to score them in parallel comes nearly for free -- SMC-SD uses idle compute to turn verification into a vectorized, fixed-size operation with no rollback. Empirically, SMC-SD achieves 2.36x speed-up over speculative decoding and a 5.2x speed-up over autoregressive decoding, while remaining within 3% of the target model's accuracy on reasoning, instruction-following, and coding benchmarks.

Yahya Emara, Mauricio Barba da Costa, Chi-Chih Chang +4

Cornell University · Makora · MIT +1

Speculative Decoding LLM Inference Acceleration

Apr 16, 2026cs.PF

Ragged Paged Attention: A High-Performance and Flexible LLM Inference Kernel for TPU

Large Language Model (LLM) deployment is increasingly shifting to cost-efficient accelerators like Google's Tensor Processing Units (TPUs), prioritizing both performance and total cost of ownership (TCO). However, existing LLM inference kernels and serving systems remain largely GPU-centric, and there is no well-established approach for efficiently mapping LLM workloads onto TPU architectures--particularly under the dynamic and ragged execution patterns common in modern serving. In this paper, we present Ragged Paged Attention (RPA), a high-performance and flexible attention kernel for TPUs, implemented using Pallas and Mosaic. RPA addresses these challenges through three key techniques: (1) fine-grained tiling to enable efficient dynamic slicing over ragged memory, (2) a custom software pipeline that fuses KV cache updates with attention computation, and (3) a distribution-aware compilation strategy that generates specialized kernels for decode, prefill, and mixed workloads. Evaluated on Llama 3 8B on TPU7x, RPA achieves up to 86% memory bandwidth utilization (MBU) in decode and 73% model FLOPs utilization (MFU) in prefill. Integrated as the primary TPU backend in vLLM and SGLang, RPA provides a production-grade foundation for efficient TPU inference and offers practical insights into kernel design.

Jevin Jiang, Ying Chen, Blake A. Hechtman +2

Google

Efficient Transformer Inference AI Accelerator Inference LLM Inference Acceleration Efficient Attention

Apr 16, 2026cs.CL

From Tokens to Steps: Verification-Aware Speculative Decoding for Efficient Multi-Step Reasoning

Speculative decoding (SD) accelerates large language model inference by allowing a lightweight draft model to propose outputs that a stronger target model verifies. However, its token-centric nature allows erroneous steps to propagate. Prior approaches mitigate this using external reward models, but incur additional latency, computational overhead, and limit generalizability. We propose SpecGuard, a verification-aware speculative decoding framework that performs step-level verification using only model-internal signals. At each step, SpecGuard samples multiple draft candidates and selects the most consistent step, which is then validated using an ensemble of two lightweight model-internal signals: (i) an attention-based grounding score that measures attribution to the input and previously accepted steps, and (ii) a log-probability-based score that captures token-level confidence. These signals jointly determine whether a step is accepted or recomputed using the target, allocating compute selectively. Experiments across a range of reasoning benchmarks show that SpecGuard improves accuracy by 3.6% while reducing latency by ~11%, outperforming both SD and reward-guided SD.

Kiran Purohit, Ramasuri Narayanam, Soumyabrata Pal

IIT Kharagpur · Adobe Research

LLM Answer Verification Speculative Decoding LLM Inference Acceleration LLM Reasoning

Apr 16, 2026cs.DC

ARGUS: Agentic GPU Optimization Guided by Data-Flow Invariants

LLM-based coding agents can generate functionally correct GPU kernels, yet their performance remains far below hand-optimized libraries on critical computations such as matrix multiplication, attention, and Mixture-of-Experts (MoE). Peak GPU performance requires coordinated reasoning over tightly coupled optimizations, including tiling, shared-memory staging, software pipelining, and instruction scheduling, while existing agents rely on sparse pass/fail feedback, leaving them unable to diagnose global constraint violations. We present Argus, an agentic framework that addresses this through data-flow invariants: compile-time specifications encoding how data must be choreographed throughout kernel execution. Argus introduces a tile-based, Pythonic DSL exposing hardware instructions and compiler policies while hiding low-level representations. The DSL provides tag functions to propagate symbolic annotations through data and control flow, and tag assertions to enforce relational constraints at use sites. When violations occur, the compiler returns concrete counterexamples identifying the thread, data element, and program point, enabling dense, structured feedback for targeted fixes. Invariants are verified at compile time via abstract interpretation over a layout algebra and SMT solving, with zero runtime overhead. An in-context reinforcement learning planner learns to select optimizations and synthesize effective invariants, supported by a curated knowledge base of GPU optimization techniques. We evaluate Argus on the AMD MI300X GPU across GEMM, flash attention, and MoE kernels accounting for over 90% of GPU time in LLM inference. Generated kernels achieve 99-104% of state-of-the-art hand-optimized assembly throughput and are 2-1543x faster than existing agentic systems. Argus further generalizes to 200 KernelBench tasks, solving 100% of Level 1 and 90% of Level 2 problems.

Haohui Mai, Xiaoyan Guo, Xiangyun Ding +7

UC Riverside5 · UCAS4 · Tsinghua University2 +2

GPU Kernel Optimization GPU Acceleration LLM-Based Program Synthesis LLM Inference Acceleration GPU Kernel Generation

Apr 16, 2026cs.AI

MemoSight: Unifying Context Compression and Multi Token Prediction for Reasoning Acceleration

While chain-of-thought (CoT) reasoning enables LLMs to solve challenging reasoning tasks, the linear growth of the KV cache leads to substantial memory and inference overhead. Existing approaches such as context compression and multi-token prediction (MTP) improve efficiency from two complementary directions by compressing historical tokens and generating future tokens in parallel. However, effectively combining them remains challenging due to their different training paradigms and architectural assumptions. In this work, we propose MemoSight (Memory-Foresight-Based Reasoning), a unified framework that integrates context compression and MTP to improve inference efficiency while preserving CoT performance. MemoSight adopts a shared minimalist design based on special tokens and token-specific positional layouts for both compression and parallel prediction. Experiments on four reasoning benchmarks show that, compared to the vanilla SFT baseline, MemoSight reduces KV cache usage by up to 66% and improves inference speed by 56%, while incurring less than a 3% drop in average reasoning accuracy, yielding a better efficiency-accuracy trade-off than existing CoT compression methods.

Xinyu Liu, Xin Liu, Bo Jin +8

School of Computer Science and Engineering, Northeastern University, China · Meituan Inc. · NiuTrans Research, Shenyang, China

Multi-Token Prediction KV Caching CoT Reasoning Memory-Efficient Optimization Memory-Efficient Inference LLM Inference Acceleration

Apr 16, 2026cs.CL

RACER: Retrieval-Augmented Contextual Rapid Speculative Decoding

Autoregressive decoding in Large Language Models (LLMs) generates one token per step, causing high inference latency. Speculative decoding (SD) mitigates this through a guess-and-verify strategy, but existing training-free variants face trade-offs: retrieval-based drafts break when no exact match exists, while logits-based drafts lack structural guidance. We propose

\textbf{RACER}

(

\textbf{R}

etrieval-

\textbf{A}

ugmented

\textbf{C}

ont

\textbf{e}

xtual

\textbf{R}

apid Speculative Decoding), a lightweight and training-free method that integrates retrieved exact patterns with logit-driven future cues. This unification supplies both reliable anchors and flexible extrapolation, yielding richer speculative drafts. Experiments on Spec-Bench, HumanEval, and MGSM-ZH demonstrate that RACER consistently accelerates inference, achieving more than

2\times

speedup over autoregressive decoding, and outperforms prior training-free methods, offering a scalable, plug-and-play solution for efficient LLM decoding. Our source code is available at

[https://github.com/hkr04/RACER](https://github.com/hkr04/RACER)

.

Zihong Zhang, Zuchao Li, Lefei Zhang +2

School of Artiﬁcial Intelligence, Wuhan University, Wuhan, China · School of Computer Science, Wuhan University, Wuhan, China · School of Information Management, Wuhan University, Wuhan, China +1

Speculative Decoding LLM Inference Acceleration Autoregressive Decoding

Apr 16, 2026cs.AI

TrigReason: Trigger-Based Collaboration between Small and Large Reasoning Models

Large Reasoning Models (LRMs) achieve strong performance on complex tasks through extended chains of thought but suffer from high inference latency due to autoregressive reasoning. Recent work explores using Small Reasoning Models (SRMs) to accelerate LRM inference. In this paper, we systematically characterize the capability boundaries of SRMs and identify three common types of reasoning risks: (1) path divergence, where SRMs lack the strategic ability to construct an initial plan, causing reasoning to deviate from the most probable path; (2) cognitive overload, where SRMs fail to solve particularly difficult steps; and (3) recovery inability, where SRMs lack robust self-reflection and error correction mechanisms. To address these challenges, we propose TrigReason, a trigger-based collaborative reasoning framework that replaces continuous polling with selective intervention. TrigReason delegates most reasoning to the SRM and activates LRM intervention only when necessary-during initial strategic planning (strategic priming trigger), upon detecting extraordinary overconfidence (cognitive offload trigger), or when reasoning falls into unproductive loops (intervention request trigger). The evaluation results on AIME24, AIME25, and GPQA-D indicate that TrigReason matches the accuracy of full LRMs and SpecReason, while offloading 1.70x - 4.79x more reasoning steps to SRMs. Under edge-cloud conditions, TrigReason reduces latency by 43.9% and API cost by 73.3%. Our code is available at https://github.com/QQQ-yi/TrigReason

Yi Zhao, Yajuan Peng, Cam-Tu Nguyen +4

AGI Institute, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · Shanghai Key Laboratory for Intelligent Information Processing, Fudan University · State Key Laboratory for Novel Software Technology, Nanjing University +2

Efficient Language Model Reasoning LLM Inference Acceleration Efficient Language Model Inference Multi-Agent Reasoning Multi-LLM Collaboration Large Reasoning Models

Apr 16, 2026cs.LG

ELMoE-3D: Leveraging Intrinsic Elasticity of MoE for Hybrid-Bonding-Enabled Self-Speculative Decoding in On-Premises Serving

Mixture-of-Experts (MoE) models have become the dominant architecture for large-scale language models, yet on-premises serving remains fundamentally memory-bound as batching turns sparse per-token compute into dense memory activation. Memory-centric architectures (PIM, NMP) improve bandwidth but leave compute underutilized under MoE's low arithmetic intensity at high batch sizes. Speculative decoding (SD) trades idle compute for fewer target invocations, yet verification must load experts even for rejected tokens, severely limiting its benefit in MoE especially at low batch sizes. We propose ELMoE-3D, a hybrid-bonding (HB)-based HW-SW co-designed framework that unifies cache-based acceleration and speculative decoding to offer overall speedup across batch sizes. We identify two intrinsic elasticity axes of MoE-expert and bit-and jointly scale them to construct Elastic Self-Speculative Decoding (Elastic-SD), which serves as both an expert cache and a strongly aligned self-draft model accelerated by high HB bandwidth. Our LSB-augmented bit-sliced architecture exploits inherent redundancy in bit-slice representations to natively support bit-nested execution. On our 3D-stacked hardware, ELMoE-3D achieves an average

6.6\times

speedup and

4.4\times

energy efficiency gain over naive MoE serving on xPU across batch sizes 1-16, and delivers

2.2\times

speedup and

1.4\times

energy efficiency gain over the best-performing prior accelerator baseline.

Yuseon Choi, Jingu Lee, Jungjun Oh +5

KAIST · Samsung Electronics · GIST

LLM Serving Mixture-of-Experts Inference Speculative Decoding LLM Inference Acceleration

Apr 16, 2026cs.LG

ConfLayers: Adaptive Confidence-based Layer Skipping for Self-Speculative Decoding

Self-speculative decoding is an inference technique for large language models designed to speed up generation without sacrificing output quality. It combines fast, approximate decoding using a compact version of the model as a draft model with selective re-evaluation by the full target model. Some existing methods form the draft model by dynamically learning which layers to skip during inference, effectively creating a smaller subnetwork to speed up computation. However, using heuristic-based approaches to select layers to skip can often be simpler and more effective. In this paper, we propose ConfLayers, a dynamic plug-and-play approach to forming the draft model in self-speculative decoding via confidence-based intermediate layer skipping. The process iteratively computes confidence scores for all layers, selects layers to skip based on an adaptive threshold, evaluates the performance of the resulting set, and updates the best selection until no further improvement is achieved or a maximum number of iterations is reached. This framework avoids the overhead and complexity of training a layer skipping policy and can provide more consistent speed-quality trade-offs while preserving the adaptivity of the draft model to diverse tasks and datasets. The performance evaluation of ConfLayers across different models and datasets shows that our novel approach offers up to 1.4x speedup over vanilla LLM generation.

Walaa Amer, Uday das, Fadi Kurdahi

Department of Electrical Engineering and Computer Sciences, University of California Irvine, Irvine, USA · Advanced Micro Devices, San Jose, USA

Speculative Decoding LLM Inference Acceleration

Apr 11, 2026cs.DC

Tessera: Unlocking Heterogeneous GPUs through Kernel-Granularity Disaggregation

Disaggregation maps parts of an AI workload to different types of GPUs, offering a path to utilize modern heterogeneous GPU clusters. However, existing solutions operate at a coarse granularity and are tightly coupled to specific model architectures, leaving much room for performance improvement. This paper presents Tessera, the first kernel disaggregation system to improve performance and cost efficiency on heterogeneous GPUs for large model inference. Our key insight is that kernels within a single application exhibit diverse resource demands, making them the most suitable granularity for aligning computation with hardware capabilities. Tessera integrates offline analysis with online adaptation by extracting precise inter-kernel dependencies from PTX to ensure correctness, overlapping communication with computation through a pipelined execution model, and employing workload-aware scheduling with lightweight runtime adaptation. Extensive evaluations across five heterogeneous GPUs and four model architectures, scaling up to 16 GPUs, show that Tessera improves serving throughput and cost efficiency by up to 2.3x and 1.6x, respectively, compared to existing disaggregation methods, while generalizing to model architectures where prior approaches do not apply. Surprisingly, a heterogeneous GPU pair under Tessera can even exceed the throughput of two homogeneous high-end GPUs at a lower cost.

Tiancheng Hu, Jin Qin, Zheng Wang +10

SCS, Peking University, Beijing, China · University of Chinese Academy of Sciences, Beijing, China · University of Leeds, West Yorkshire, England +4

GPU Acceleration LLM Inference Acceleration Heterogeneous Computing

Apr 9, 2026cs.DC

SMART: When is it Actually Worth Expanding a Speculative Tree?

Tree-based speculative decoding accelerates autoregressive generation by verifying a branching tree of draft tokens in a single target-model forward pass. However, existing methods prioritize maximizing token-level likelihood or the number of accepted tokens while ignoring a critical ``efficiency paradox'': the computational overhead of drafting and verifying big trees can grow super-linearly, particularly at scale. This often leads to negative wall-clock speedup when batch sizes increase or hardware saturation limits are reached. To address this, we propose SMART, a system-aware marginal analysis framework for runtime tree construction. SMART reformulates tree expansion as a hardware-aware optimization problem that directly maximizes end-to-end speedup. By applying a principled marginal benefit--cost rule at inference time, SMART expands a node only when its marginal benefit--cost ratio exceeds the tree-level speedup. SMART is training-free and serves as a plug-and-play controller for existing frameworks like MSD and EAGLE. Extensive evaluations across three MLLMs (e.g., LLaVA, Qwen2-VL) and four LLMs (e.g., Llama-3.1, DeepSeek-R1) demonstrate that SMART consistently outperforms state-of-the-art baselines. It delivers an average additional speedup of 20.0% for MLLMs and 15.4% for LLMs across compute-bound batching regimes and diverse GPU architectures without performance loss.

Lifu Wang, Pan Zhou

Singapore Management University, Singapore

Inference-Time Optimization GPU Acceleration Efficient VLM Inference Speculative Decoding LLM Inference Acceleration

Apr 8, 2026cs.LG

Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference

The quadratic computational complexity of standard attention mechanisms presents a severe scalability bottleneck for LLMs in long-context scenarios. While hybrid attention mechanisms combining Full Attention (FA) and Sparse Attention (SA) offer a potential solution, existing methods typically rely on static allocation ratios that fail to accommodate the variable retrieval demands of different tasks. Furthermore, head-level dynamic sparsity often introduces severe computational load imbalance and synchronization long-tails, which hinder hardware acceleration during autoregressive decoding. To bridge this gap, we introduce Flux Attention, a context-aware framework that dynamically optimizes attention computation at the layer level. By integrating a lightweight Layer Router into frozen pretrained LLMs, the proposed method adaptively routes each layer to FA or SA based on the input context. This layer-wise routing preserves high-fidelity information retrieval while ensuring contiguous memory access, translating theoretical computational reductions into practical wall-clock speedups. As a parameter-efficient approach, our framework requires only 12 hours of training on 8

\times

A800 GPUs. Extensive experiments across multiple long-context and mathematical reasoning benchmarks demonstrate that Flux Attention achieves a superior trade-off between performance and inference speed compared with baseline models, with speed improvements of up to

2.8\times

and

2.0\times

in the prefill and decode stages.

Quantong Qiu, Zhiyi Hong, Yi Yang +5

School of Computer Science and Technology, Soochow University · Baidu Inc, China

Self-Attention Long-Context Language Model Inference LLM Inference Acceleration Sparse Attention Attention Mechanisms Hybrid Attention

Apr 1, 2026cs.LG

Screening Is Enough

We call query--key relevance absolute when its values lie on a fixed bounded scale, depend on neither competing keys nor sequence length, require no sequence-length-dependent calibration, and can all be zero. To realize this notion, we introduce screening, whose explicit threshold transforms bounded query--key similarities into relevance values, enabling exact rejection, empty selection, and direct inspection on a common scale. In a controlled comparison of 12 attention mechanisms on a matched Transformer backbone, only screening maintains both low long-context perplexity and robust retrieval beyond the training context; notably, it does so without inference-time scaling. Building on screening, we introduce Multiscreen, a language-model architecture composed of parallel gated screening tiles. Multiscreen retains these long-context gains while achieving greater parameter efficiency, stronger general zero-shot downstream performance, lower training cost at larger scales, and lower model-side time to first token than Transformer baselines. We further develop a normalization design that keeps Multiscreen training stable even at a learning rate of

1

and show that an adapted version likewise stabilizes Transformer at the same learning rate.

Ken M. Nakanishi

Center for Emergent Matter Science (CEMS), RIKEN · Graduate School of Science, The University of Tokyo

Self-Attention Long-Context Language Modeling Transformer Attention LLM Inference Acceleration Attention Mechanisms

Apr 1, 2026cs.PL

Executing as You Generate: Hiding Execution Latency in LLM Code Interpreters

Current LLM systems are increasingly equipped with a code interpreter that executes generated code to obtain results. This works serially: the model first generates the complete code, then an interpreter executes it. This sequential workflow leaves the executor idle during generation and the generator idle during execution, resulting in unnecessary end-to-end latency. Our key observation is that an LLM, unlike a human developer, emits code tokens left to right and does not backtrack over what it has already written. This makes it possible to start executing a piece of code while later tokens are still being generated. We formalize this parallel execution paradigm, modeling it as a three-stage pipeline of generation, detection, and execution, and derive closed-form latency bounds that characterize its speedup potential and operating regimes. We then present EAGER, a concrete implementation featuring AST-based chunking, dynamic batching with gated execution, and early error interruption. We evaluate EAGER across four benchmarks, seven LLMs, and three execution environments. The overlap mechanism hides almost all execution behind generation, reducing the non-overlapped portion of execution time by up to 99.8% and cutting end-to-end latency by up to 37.3% on error-free runs.

Zhensu Sun, Zhihao Lin, Zhi Chen +4

Singapore Management University · Beihang University

LLM Inference Acceleration Pipeline Parallelism LLM Code Generation

Mar 30, 2026cs.LG

HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention

Token-level sparse attention mechanisms, exemplified by DeepSeek Sparse Attention (DSA), achieve fine-grained key selection by scoring every historical key for each query through a lightweight indexer, then computing attention only on the selected subset. While the downstream sparse attention itself scales favorably, the indexer must still scan the entire prefix for every query, introducing an per-layer bottleneck that grows prohibitively with context length. We propose HISA (Hierarchical Indexed Sparse Attention), a plug-and-play replacement for the indexer that rewrites the search path from a flat token scan into a two-stage hierarchical procedure: (1) a block-level coarse filtering stage that scores pooled block representations to discard irrelevant regions, followed by (2) a token-level refinement stage that applies the original indexer exclusively within the retained candidate blocks. HISA preserves the identical token-level top-sparse pattern consumed by the downstream Sparse MLA operator and requires no additional training. On kernel-level benchmarks, HISA achieves up to speedup at 64K context. On Needle-in-a-Haystack and LongBench, we directly replace the indexer in DeepSeek-V3.2 and GLM-5 with our HISA indexer, without any finetuning. HISA closely matches the original DSA in quality, while substantially outperforming block-sparse baselines.

Yufei Xu, Fanxu Meng, Fan Jiang +11

Xiaohongshu

Self-Attention LLM Inference Acceleration Efficient Attention Sparse Attention Attention Mechanisms

Mar 24, 2026cs.CV

SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning

Agentic multimodal large language models (MLLMs) (e.g., OpenAI o3 and Gemini Agentic Vision) achieve remarkable reasoning capabilities through iterative visual tool invocation. However, the cascaded perception, reasoning, and tool-calling loops introduce significant sequential overhead. This overhead, termed agentic depth, incurs prohibitive latency and seriously limits system-level concurrency. To this end, we propose SpecEyes, an agentic-level speculative acceleration framework that breaks this sequential bottleneck. Our key insight is that a lightweight, tool-free MLLM can serve as a speculative planner to predict the execution trajectory, enabling early termination of expensive tool chains without sacrificing accuracy. To regulate this speculative planning, we introduce a cognitive gating mechanism based on answer separability, which quantifies the model's confidence for self-verification without requiring oracle labels. Furthermore, we design a heterogeneous parallel funnel that exploits the stateless concurrency of the small model to mask the stateful serial execution of the large model, maximizing system throughput. Extensive experiments on V* Bench, HR-Bench, and POPE demonstrate that SpecEyes achieves 1.1-3.35x speedup over the agentic baseline while preserving or even improving accuracy (up to +6.7%), thereby boosting serving throughput under concurrent workloads.

Haoyu Huang, Jinfa Huang, Zhongwei Wan +3

Xiamen University, Xiamen, Fujian, China · University of Rochester, Rochester, NY, USA · The Ohio State University, Columbus, OH, USA

Efficient Multimodal Inference LLM Inference Acceleration Multimodal Agents

Mar 18, 2026cs.CL

Learning When to Attend: Conditional Memory Access for Long-Context LLMs

Language models struggle to generalize beyond pretraining context lengths, limiting long-horizon reasoning and retrieval. Continued pretraining on long-context data can help but is expensive due to the quadratic scaling of Attention. We observe that most tokens do not require (Global) Attention over the entire sequence and can rely on local context. Based on this, we propose L2A (Learning To Attend), a layer that enables conditional (token-wise) long-range memory access by deciding when to invoke global attention. We evaluate L2A on Qwen 2.5 and Qwen 3 models, extending their effective context length from 32K to 128K tokens. L2A matches the performance of standard long-context training to within 3% while skipping Global Attention for

\sim

80% of tokens, outperforming prior baselines. We also design custom Triton kernels to efficiently implement this token-wise conditional Attention on GPUs, achieving up to

\sim

2

\times

improvements in training throughput and time-to-first-token over FlashAttention. Moreover, L2A enables post-training pruning of highly sparse Global Attention layers, reducing KV cache memory by up to 50% with negligible performance loss. Our code is released under Apache 2.0 at https://github.com/awslabs/hybrid-model-factory/tree/main/examples/research/L2A.

Sakshi Choudhary, Aditya Chattopadhyay, Luca Zancato +4

Department of Electrical and Computer Engineering, Purdue University, USA · AWS Agentic AI, USA

Self-Attention Long-Context Language Modeling LLM Inference Acceleration Sparse Attention Attention Mechanisms

Mar 10, 2026cs.CR

FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation

Device-side Large Language Models (LLMs) have witnessed explosive growth, offering higher privacy and availability compared to cloud-side LLMs. During LLM inference, both model weights and user data are valuable, and attackers may even compromise the OS kernel to steal them. ARM TrustZone is the de facto hardware-based isolation technology on mobile devices, used to protect sensitive applications from a compromised OS. However, protecting LLM inference with TrustZone incurs significant overhead due to its inflexible isolation of memory and the NPU. To address these challenges, this paper introduces FlexServe, a fast and secure LLM serving system for mobile devices. It first introduces a Flexible Resource Isolation mechanism to construct Flexible Secure Memory (Flex-Mem) and Flexible Secure NPU (Flex-NPU). Both memory pages and the NPU can be efficiently switched between unprotected and protected modes. Based on these mechanisms, FlexServe designs a fast and secure LLM inference framework within TrustZone's secure world. The LLM-Aware Memory Management and Secure Inference Pipeline are introduced to accelerate inference. A Multi-Model Scheduler is proposed to optimize multi-model workflows. We implement a prototype of FlexServe and compare it with two TrustZone-based strawman designs. The results show that FlexServe achieves an average

10.05\times

speedup in Time to First Token (TTFT) compared to the strawman, and an average

2.44\times

TTFT speedup compared to an optimized strawman with pipeline and secure NPU enabled. For multi-model agent workflows, the end-to-end speedup is up to

24.30\times

and

4.05\times

compared to the strawman and optimized strawman, respectively.

Yinpeng Wu, Yitong Chen, Lixiang Wang +3

Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University

LLM Serving On-Device Language Model Inference Trusted Execution Environments LLM Security LLM Inference Acceleration