On-Device Language Model Inference

Momentum

23 papers in the last four weeks, up 229% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 111

Jun 22, 2026cs.CR

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

Device-side Large Language Models (LLMs) have grown explosively, offering stronger privacy and higher availability than their cloud-side counterparts. During LLM inference, both the model weights and the user data are valuable, and attackers may 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 to both the secure inference and the normal aplications, due to two challenges: the inflexible resource isolation and the inefficient secure resource management. To address these challenges, this paper presents FlexServe, a fast and secure LLM inference system for mobile devices. The key idea is to decouple the access permission from the management permission of secure resources, so that the normal-world OS cannot access them but can still manage them as usual. First, FlexServe introduces a Recallable Resource Isolation mechanism to construct Recallable Secure Memory (Flex-Mem) and a Recallable Secure NPU (Flex-NPU). They can only be accessed by the secure world, but can be efficiently allocated and reclaimed by the normal-world OS. Based on them, FlexServe further introduces a FlexServe Framework to run secure LLM inference in the secure world. It works together with the normal-world OS to perform cooperative secure memory management. We implement a prototype of FlexServe and compare it with two TrustZone-based strawman designs. The results show that FlexServe achieves average TTFT speedups of 10.05X over the strawman and 2.44X over an optimized strawman.

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

Ask PDF

Jun 22, 2026cs.SE

EnerInfer: Energy-Aware On-Device LLM Inference

On-device LLM inference is increasingly attractive for privacy-preserving, reliable, and cost-effective deployment, yet its energy and thermal costs remain a critical bottleneck. Existing systems primarily optimize for decoding speed, implicitly assuming that faster execution is always preferable. We show instead that on-device LLM inference often has exploitable configuration slack: modestly lowering NPU and memory frequencies preserves quality of experience (QoE) while substantially improving energy efficiency and reducing heat. Realizing this opportunity in production is challenging. The most energy-efficient NPU/DDR setting varies with the model, inference engine, platform, and runtime conditions, with no stable ranking across configurations. Commercial devices further lack component-level power sensing, and shell temperature evolves with request arrivals, response lengths, and thermal history. To address these challenges, we propose EnerInfer, the first on-device LLM inference framework that jointly manages energy efficiency, throughput, and thermal comfort for LLM workloads. EnerInfer replaces per-model profiling and sensor-heavy control with disaggregated, model-structure-aware prediction and ranking-driven online feedback. It predicts throughput and power for unseen LLMs across NPU/DDR frequency settings, selects QoE-satisfying efficient configurations under runtime interference, and uses lightweight limited-horizon thermal prediction to dynamically switch between energy-optimized and thermally constrained inference. Evaluations on real-world LLMs show that EnerInfer improves energy efficiency by up to 65%, 12%, and 24% on phones, a laptop, and a development board, respectively, without QoE violation.

Bohua Zou, Nian Liu, Binqi Sun +6

Technical University of Munich · Shanghai Jiao Tong University · Huawei Hilbert Research Center (Dresden) +1

On-Device Language Model Inference LLM Inference Acceleration Efficient Language Model Inference

Ask PDF

Jun 21, 2026cs.PF

Enabling Cloud-Level Accuracy in Edge AI through IoT Data Preprocessing

Large language models (LLMs) offer a natural-language interface for interpreting Internet of Things (IoT) sensor data in smart environments; however, cloud deployment introduces latency, privacy, and connectivity concerns. Local LLMs can reduce these limitations, but compact edge-deployable models often show weaker numerical reasoning when raw sensor readings are provided directly. This paper investigates whether prompt-side preprocessing can improve the accuracy-latency trade-off of local LLMs for environmental monitoring. We propose a structured prompt construction framework that transforms raw air-quality and thermal-comfort measurements into progressively enriched textual representations: raw sensor values, threshold-aware descriptions, and compact environmental summary flags. The approach is evaluated using indoor Raspberry Pi/BME680 datasets from Tampere University and outdoor air-quality datasets from Helsinki, Katowice, and Warsaw. We construct a binary LLM query dataset covering air quality, thermal comfort, and joint environmental conditions, and evaluate five local and five cloud LLMs across three prompt variants and two inference modes, with and without chain-of-thought prompting. Results show that prompt enrichment substantially improves local-model accuracy. In No-CoT mode, local accuracy increases from 50.9% to 81.7% indoors and from 63.7% to 89.3% outdoors from the raw to the most enriched prompt. Local No-CoT inference is the fastest configuration, with mean latency close to 0.22 s, while CoT substantially increases inference time. These findings suggest that lightweight prompt-side preprocessing can narrow the local--cloud performance gap and support low-latency IoT analytics in smart environments.

Aygün Varol, Katarzyna Kołodziej, Łukasz Sobczak +5

Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland · Institute of Theoretical and Applied Informatics, Polish Academy of Sciences, Gliwice, Poland · Department of Computer Science, University of Helsinki, Helsinki, Finland +1

On-Device Language Model Inference LLM Prompting Internet of Things

Ask PDF

Jun 19, 2026cs.PF

Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study

Mixture-of-Experts (MoE) language models are often described as ideal for resource-constrained inference. Each token activates only a small subset of experts, so the per-token compute cost, in floating-point operations (FLOPs), resembles that of a much smaller dense model. Whether that FLOP advantage survives in practice is far less clear. We ask whether MoE models actually run faster and cheaper than comparable dense models on consumer-grade and edge hardware. We benchmark OLMoE-1B-7B (1.3 B active of 6.9 B total) against three dense baselines on an Apple M2 Pro and an NVIDIA Jetson Orin Nano 8 GB through llama

.

cpp, measuring throughput, memory, and on-device energy. The answer is device-dependent: OLMoE's active-parameter advantage is only partly realised on the laptop (~10% behind the same-active Llama-3.2-1B) and erodes on the edge device (~31% behind, at 2.1

\times

the energy per token, with peak memory at the 8 GB ceiling). Patching llama

.

cpp to time the decode graph node-by-node shows routing accounts for under 9% of MoE-block compute on the cleaner edge backend, so the gap reflects total-parameter memory footprint, expert dispatch, and KV-cache pressure rather than routing. The implication is that on bandwidth-bound edge hardware, inference cost tracks total parameters, not active ones, and sparse activation does not buy back what the device is constrained on. These findings are bounded to one MoE model at this parameter scale and two devices, and we release the full measurement harness and per-run data.

Alfarizy Alfarizy, Hung Truong Thanh Nguyen, René Richard +2

Analytics Everywhere Lab, University of New Brunswick, Fredericton, NB, Canada · TSAI Lab, University of New Brunswick, Fredericton, NB, Canada

LLM Inference Efficiency On-Device Language Model Inference Energy-Efficient ML Edge Inference Mixture-of-Experts Inference

Ask PDF

Jun 17, 2026cs.LG

MawForge: Memory-Bounded Expert Materialization for Local Mixture-of-Experts Inference

Sparse Mixture-of-Experts (MoE) language models separate total parameter count from per-token active computation, but local inference systems often still require the full model, key-value cache, runtime buffers, and operatingsystem headroom to fit in fast memory. MawForge tests a different systems hypothesis: local MoE serving can be made practical on constrained unified-memory machines by storing the full model on disk, keeping common tensors resident, and materializing routed expert tensors into a bounded execution cache on demand. The central finding is that MawForge is effective as a bounded execution mechanism and measurement substrate for local MoE inference, but not as a cache-maximization policy. Performance depends on balancing expert reuse against resident footprint, KV-cache size, quantization, route locality, and macOS memory pressure.

Craig Opie

Holocron Security, Inc.

Expert Offloading On-Device Language Model Inference Mixture-of-Experts Inference Memory-Efficient Inference

Ask PDF

Jun 11, 2026cs.LG

Efficient On-Device Diffusion LLM Inference with Mobile NPU

Diffusion large language models (dLLMs) accelerate generation by denoising multiple tokens in parallel, making them attractive for latency-sensitive mobile inference. However, repeated denoising introduces substantial computation on smartphones. Mobile neural processing units (NPUs) offer high-throughput dense matrix computation, but efficiently exploiting them remains challenging: token commitment shrinks per-block effective workloads, token revision complicates KV cache reuse, and limited NPU-visible address space incurs costly remapping and data transfer overheads. In this paper, we propose llada.cpp, the first NPU-aware inference framework for accelerating dLLMs on smartphones. llada.cpp aligns block-wise dLLM inference with the execution characteristics of mobile NPUs through three techniques. (1) Multi-Block Speculative Decoding fills the shrinking workload in late-stage current-block decoding with speculative future-block tokens. (2) Dual-Path Progressive Revision keeps committed tokens revisable until stable and refreshes unstable tokens through a CPU-side path without stalling dense NPU execution. (3) Swap-Optimized Memory Runtime compacts NPU-visible address layouts and overlaps data staging with NPU computation to reduce remapping and transfer overheads. We implement llada.cpp as an end-to-end framework and evaluate it across diverse hardware platforms and dLLM workloads. llada.cpp reduces LLaDA-8B generation latency by 17x-42x over the CPU baseline with prefix KV cache reuse, while preserving generation quality.

Tuowei Wang, Yanfan Sun, Ju Ren

Beihang University China · Tsinghua University China

AI Accelerator Inference On-Device Language Model Inference Speculative Decoding Diffusion Language Model Inference Diffusion Language Model Decoding

Ask PDF

Jun 10, 2026cs.LG

Closing the Social-Semantic Gap: SPSD for Edge-Based Prompt Compression in Cloud LLM Inference

The prefill stage of Large Language Model (LLM) inference is a growing contributor to cloud-scale energy cost. Many consumer-support and conversational prompts contain social scaffolding: politeness markers, apologetic preamble, repetition, and rapport-building language that is important for human communication but carries low marginal information for machine reasoning. We call this discrepancy the Social-Semantic Gap. We present SPSD (Sentiment Preserving Semantic Distillation), an edge-based pipeline that compresses user prompts using a 4-bit quantised Small Language Model before transmission to a cloud-deployed LLM. Evaluation on a 248-prompt corpus using Gemma-2-2B-Instruct (Q4_K_M) as the SLM and Llama-3.1-8B-Instruct as the cloud evaluation model yields a mean input token saving of 99.9 tokens per distilled call, with all 146 distilled calls yielding positive savings. Response quality, assessed by blind LLM-as-judge scoring across 121 pairs, is non-inferior to the raw path within a pre-specified 1-point margin on a 15-point rubric; the judge awarded 43 percent ties, 28 percent distilled wins, and 29 percent raw wins. Cosine similarity is mixed: mean 0.682, median 0.712, with 54.1 percent of pairs above the 0.70 reference threshold. Safety-critical domains are conservatively routed to passthrough via rule-based gates. Per-call net energy saving is estimated at 70-270 uWh under stated assumptions. SPSD shows that on-device prompt distillation can reduce cloud LLM input-token cost while preserving response quality within a practical non-inferiority margin.

Abhinit Sen, Ajeet Kumar, Manaranjan Pradhan

Indian School of Business, Hyderabad, India

LLM Inference Efficiency On-Device Language Model Inference Language Model Distillation Prompt Compression

Ask PDF

Jun 9, 2026cs.DC

TileFuse: A Fused Mixed-Precision Kernel Library for Efficient Quantized LLM Inference on AMD NPUs

With the growing demand for on-device LLM inference, edge SoCs increasingly integrate NPUs to improve performance and energy efficiency under tight power and thermal budgets. However, practical LLM deployment on current client NPUs remains difficult: widely used quantization formats such as AWQ do not map cleanly onto many existing NPU software stacks, which are often proprietary and expose limited low-level control. In this work, we present TileFuse, a close-to-metal mixed-precision kernel library for AMD XDNA2 NPUs that targets GEMM/GEMV-based operators in quantized LLM inference. TileFuse brings practical low-bit formats such as AWQ-style W4A16 and W8A16 directly onto XDNA2, rather than forcing the model to be reshaped around an NPU-specific quantization scheme. TileFuse co-designs weight layout, metadata placement, mixed-precision microkernels, and array-level dataflow. Specifically, it fuses unpacking, dequantization, and GEMM/GEMV execution into a single kernel flow, introduces an interleaved pre-tiling layout that supports GEMM dimensions up to 32K, and redesigns GEMV dataflow to utilize the full 4x8 AIE array. Across kernel-level evaluations, TileFuse improves performance by up to 121.6% for GEMM and 281% for GEMV over full-precision baselines, while delivering more than 2x performance and energy-efficiency gains over strong iGPU baselines on GEMM. In end-to-end LLM experiments on Ryzen AI laptops, TileFuse achieves up to 2.0x lower prefilling latency with more than 64.6% lower energy consumption. Together, these results show that XDNA2 is a practical target for AWQ-style edge LLM inference and that native NPU support for off-the-shelf quantization can make NPUs substantially more usable in real client deployments.

Wesley Pang, Gregory Hyegang Jun, Feiyang Liu +1

University of Illinois Urbana-Champaign Department of Electrical and Computer Engineering USA

Mixed-Precision Quantization LLM Quantization AI Accelerator Inference On-Device Language Model Inference LLM Inference

Ask PDF

Jun 9, 2026cs.DC

Achieving Cloud-Grade SLOs for Local Mixture-of-Experts Inference through CPU-GPU Hybrid Design

Local deployment of large Mixture-of-Experts (MoE) models falls short of the service quality achieved in cloud-scale environments, even under low-concurrency workloads. We identify four key gaps in local MoE inference: reliance on capacity-reduced models (quantized, distilled, rerouted), inability to meet 30-second TTFT for long prefills (more than 12K), sub-baseline decode throughput (under 20 tokens/s), and poor concurrency under mixed prefill-decode and batched decode workloads. We present a CPU-GPU hybrid system that achieves cloud-level SLOs on dual-socket commodity CPUs and consumer GPUs by (1) stream-loading prefill (SLP), boosting prefill throughput to 1,200 tokens/s and enabling 32K prompts within 30 seconds; (2) distributed SLP (DSLP) with SmallEP expert parallelism, reaching 1,800 tokens/s and 45K prompts in 30 seconds on two RTX 5090s; (3) intra-node prefill-decode disaggregation with zero-copy shared weights and a dual-batch attention-MoE overlap scheme, sustaining concurrency with under 15 percent latency increase and 50 percent throughput gains; (4) an AVX-512-optimized FP8 GEMV kernel, enabling native CPU FP8 inference while delivering 4-5x lower CPU latency; and (5) fine-grained CPU parallelism that attains 28 tokens/s on INT4 DeepSeek-V3 and 21.5 tokens/s on intact FP8 V3. Evaluations show our system delivers cloud-level QoS for flagship MoE models on consumer CPU-GPU platforms, reshaping local deployment with intact, original-precision inference and enabling high-quality, cost-effective access without datacenter infrastructure.

Wenxin Wang, Yule Hou, Yu Ji +2

1Tsinghua University · 2Xingyun Integrated Circuits Co., Ltd. · 3Beijing National Research Center for Information Science and Technology

Expert Parallelism On-Device Language Model Inference Mixture-of-Experts Inference LLM Inference Serving Heterogeneous Computing

Ask PDF

Jun 8, 2026cs.LG

Distilling Safe LLM Systems via Soft Prompts for On Device Settings

Deploying safe large language models (LLMs) on resource-constrained edge devices presents a critical challenge: while dual-model systems combining LLMs with guard models provide effective safety guarantees, their substantial memory and computational demands make them prohibitively expensive for on-device deployment. This paper presents a comprehensive study of parameter-efficient safety alignment methods for resource-constrained settings. Through systematic evaluation across multiple LLM architectures, training objectives, and parameter-efficient fine-tuning approaches, we identify that soft prompts combined with distillation-based training consistently outperform alternative methods. We introduce distillation frameworks based on total variation and KL divergence that effectively transfer safety behaviors from guard models into learned soft prompts. Our evaluations on various benchmarks demonstrate that this combination achieves superior safety-usefulness trade-offs compared to LoRA adapters, steering vectors, and direct optimization methods, while requiring minimal additional memory and compute at inference time. These findings establish soft prompt distillation as the preferred approach for safety alignment in on-device LLM deployment.

Motasem Alfarra, Cristina Pinneri, Dana Kianfar +2

Qualcomm AI Research

On-Device Language Model Inference LLM Safety Alignment Prompt Tuning Language Model Distillation

Ask PDF

Jun 3, 2026cs.DC

Multi-SPIN: Multi-Access Speculative Inference for Cooperative Token Generation at the Edge

Speculative inference (SPIN) was originally developed as an efficient architecture to accelerate Large Language Models (LLMs). In this work, we propose its distributed deployment to enable cooperative token generation in a multiuser edge system; its advantage is to effectively balance computational loads between resource-constrained devices and servers. The resulting architecture, termed Multi-access SPIN (Multi-SPIN), utilizes on-device small language models to generate and upload candidate token drafts, while an edge server operates the LLM to verify them in parallel batches. Given the severe heterogeneity in users' computation and communication capabilities, the draft length emerges as a critical control variable that influences node-level computation loads and multi-access latency, thereby governing the sum token goodput. Consequently, considering frequency-division multiple access, we investigate the problem of multi-access draft control, a joint optimization of draft-length control and bandwidth allocation to maximize sum token goodput. We examine two cases: (1) homogeneous draft lengths across users to facilitate server-side batching, and (2) heterogeneous draft lengths to introduce a new dimension for goodput enhancement. By developing decomposition methods, we reduce these complex optimizations into tractable sub-problems, which allow efficient draft control algorithms to be derived in closed form. Our analysis shows that the optimal bandwidth allocation compensates users with weaker computation-and-communication capabilities in the homogeneous case due to the batching synchronization requirements, whereas its heterogeneous-case counterpart rewards users with higher acceptance rates by relaxing such requirements. Experiments using Llama-2 and Qwen3.5 model pairs across diverse tasks demonstrate that Multi-SPIN improves goodput by up to 88% over heterogeneity-agnostic baselines.

Haotian Zheng, Zhanwei Wang, Mingyao Cui +3

Department of Electrical and Computer Engineering, The University of Hong Kong, Hong Kong SAR, China

On-Device Language Model Inference Edge Computing Speculative Decoding LLM Inference Acceleration Wireless Resource Allocation Distributed Inference

Ask PDF

Jun 3, 2026cs.LG

Operator Fusion for LLM Inference on the Tensix Architecture

This study addresses on-device inference bottlenecks of Transformer models on Tenstorrent's Tensix architecture and proposes an operator fusion strategy that enhances data locality. RMSNorm is fused with matrix multiplication in self-attention and in the FFN, enabling back-to-back execution of memory-bound and compute-bound operators in on-chip SRAM to significantly reduce DRAM reads/writes of intermediate results and scheduling overhead. To support multi-core parallelism, a NoC-based multicast mechanism is leveraged in which row/column master nodes efficiently distribute inputs and weights across the core mesh, alleviating DRAM bandwidth contention. Experiments on the Wormhole platform with Qwen2.5-0.5B, Qwen3-0.6B, and Qwen3-4B show up to 37.44% latency reduction for attention and 15.89% for MLP, with up to 7.91% reduction per decoder layer, while Pearson Correlation Coefficient (PCC) remains above 98.75%, confirming significant end-to-end efficiency gains under numerical consistency.

Qingbo Wu, Ke Li, Wenzhu Wang +3

KylinSoft Co., Ltd, Tianjin, China · openKylin Community, Tianjin, China · College of Computer Science and Technology, National University of Defense Technology, Changsha, China

Efficient Transformer Inference AI Accelerator Inference On-Device Language Model Inference Memory-Efficient Inference

Ask PDF

Jun 2, 2026cs.LG

LLM Compression with Jointly Optimizing Architectural and Quantization choices

Deploying large language models (LLMs) is challenging due to their significant memory and computational requirements. While some methods address this by developing small or tiny language models from scratch, these approaches demand extensive GPU training. Compressing pre-trained LLMs for edge devices offers a compelling alternative. Beyond pruning and quantization, Neural Architecture Search (NAS) enables effective compression, yet prior NAS approaches often limit the search space and decouple architecture from quantization. We introduce a differentiable NAS framework that explores the entire space and jointly optimizes architectural configurations alongside mixed-precision quantization for linear layers of LLMs. Experiments demonstrate superior accuracy-latency trade-offs: our models achieve up to 1.4x faster inference than sequential NAS-then-quantization baselines at comparable accuracy, or up to 6% higher average accuracy across seven reasoning tasks at equivalent latency.

Hoang-Loc La, Truong-Thanh Le, Amir Taherkordi +1

UiT The Arctic University of Norway · University of Oslo, Norway

Mixed-Precision Quantization LLM Quantization On-Device Language Model Inference LLM Compression Neural Architecture Search

Ask PDF

Jun 2, 2026cs.NE

Spike-Aware INT8 Execution for Spiking Language Models on Commodity CPUs

Binary spike activations allow a language-model runtime to read only active weight columns and replace multiplications by weight sums. We implement this execution strategy in C++ for an 874M-parameter spike-gated language model. Sparse projections use column-major INT8 weights, integer accumulation, and one scale application per output channel; dense projections retain row-major access and FP32 activations. In a single-thread comparison using an early checkpoint, INT8 achieves 23.31 tokens/s versus 9.82 for FP32, while reducing weight storage from 3355.2 to 1087.4 MiB. A variant using INT4 on dense projections saves a further 17.4% of storage but reduces decode throughput by 46.6%. On an AMD Ryzen 7 5800X, the final INT8 checkpoint achieves 22.63 tokens/s on one thread and 47.90 on four threads; 512-token prefill reaches 94.68 tokens/s on eight threads. A separate ARM output-head case study records higher trimmed decode-window energy metrics for two candidate-verification configurations. The results characterize how activation-specific layouts and quantized kernels support CPU deployment of a spike-gated language model.

Ting Liu

SymbolicLight Research Foshan, Guangdong, China

LLM Quantization On-Device Language Model Inference Activation Sparsity LLM Inference Acceleration Spiking Neural Networks Language Modeling

Ask PDF

May 29, 2026cs.CL

Translation Analytics for Freelancers II: Benchmarking Local LLMs for Confidential Translation Workflows

Building on our previous work, this paper develops practical, low-barrier methods for freelance translators and smaller language service providers to evaluate translation technologies using rigorous yet accessible analytic methods. Here we address a high-stakes, specialized need: offline translation for confidentiality-sensitive domains in which privacy constraints preclude the use of cloud-based engines and commercial LLMs. We expand the Reeve Foundation Trilingual Corpus (RFTC) used in our previous work into a multilingual corpus (RFMC) by adding sentence-aligned German and Simplified Chinese reference translations. We then benchmark several locally runnable language models (via Ollama) across four language directions on 1000+ sentences selected from this corpus. We use consistent single-prompt calls without fine-tuning or domain adaptation, comparing local LLM outputs against commercial NMTs (DeepL, Baidu), a frontier LLM (GPT-5.2), and professional-grade local NMT systems (OPUS-CAT, NeuralDesktop, Promt). Automatic evaluation is conducted with MATEO. Results reveal substantial variation in local LLM performance across language directions and model sizes. The best local LLMs match or surpass local NMT systems and a frontier LLM, though they remain behind top commercial NMTs. These findings underscore the viability of carefully selected local LLM translation for privacy-constrained professionals and inform future research on model scaling and multilingual capability.

Yuri Balashov, Rex VanHorn, Mingxi Xu +1

University of Georgia, Athens, Georgia, USA

Multilingual Language Model Evaluation On-Device Language Model Inference Privacy-Preserving Language Models Machine Translation MT Evaluation

Ask PDF

May 28, 2026cs.MA

When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems

The design space of agentic AI inference spans two extremes: frontier large language models (LLMs), typically hosted in the cloud and offering strong performance across a wide range of tasks at substantially high cost, and more cost-efficient small language models (SLMs), which are amenable to on-device inference. Hybrid multi-agent systems (MASs) combining on-device and cloud models offer a promising middle ground, but they also introduce a complex and poorly understood design space in which task accuracy, monetary cost, and edge energy consumption are tightly coupled; in the absence of general design principles, hybrid components, although not the most prevalent choice, are typically introduced through ad hoc decisions tailored to specific domains. In this work, we examine this design space more systematically. We adapt two representative MAS architectures to support hybrid inference and study how individual design choices shift the operating point along the Pareto frontier of power, cost, and performance. Our findings paint a nuanced picture of hybrid MAS design: while SLMs can effectively benefit from LLM assistance, the optimal architecture is highly task-dependent, and greater frontier-level compute does not consistently translate to better performance.

Corrado Rainone, Davide Belli, Bence Major +1

Qualcomm Technologies, Inc. 1Qualcomm AI Research†

Multi-Agent LLM Systems On-Device Language Model Inference Cost-Aware Inference

Ask PDF

May 26, 2026cs.LG

MobileMoE: Scaling On-Device Mixture of Experts

Mixture-of-Experts (MoE) has become the de facto architecture for hundred-billion-parameter language models, yet its advantages at sub-billion scales for on-device deployment remain largely unexplored. To close this gap, we present MobileMoE, a family of on-device MoE language models with sub-billion active parameters (0.3-0.9B active and 1.3-5.3B total) that establish a new Pareto frontier for on-device LLMs. We first formulate an on-device MoE scaling law that jointly optimizes MoE architecture under mobile memory and compute constraints, identifying an on-device sweet spot - moderate sparsity with fine-grained and shared experts - that is simultaneously memory and compute-optimal. Building on the derived architectures, we train MobileMoE with a four-stage recipe covering pre-training, mid-training, instruction fine-tuning, and quantization-aware training, all on open-source datasets. Across 14 benchmarks, MobileMoE matches or exceeds leading on-device dense LLMs with 2-4

\times

fewer inference FLOPs, and matches or surpasses the state-of-the-art MoE OLMoE-1B-7B with up to 60% fewer parameters. To bridge the last mile to mobile deployment, we provide the first efficient MoE inference on commodity smartphones with comprehensive on-device profiling. At comparable INT4 weight memory, MobileMoE-S delivers

1.8

3.8\times

faster prefill and

2.2

3.4\times

faster decode than the dense baseline MobileLLM-Pro.

Yanbei Chen, Hanxian Huang, Ernie Chang +5

Meta AI

Mixture-of-Experts Language Models On-Device Language Model Inference Mixture-of-Experts Inference Efficient Language Model Inference AI Scaling Laws

Ask PDF

May 26, 2026cs.LG

Dense2MoE: Pushing the Pareto Frontier of On-Device LLMs via Unified Pruning and Upcycling

The Mixture of Experts MoE architecture is highly promising for resource constrained on device deployments yet training these models from scratch incurs prohibitive costs Current methods attempt to alleviate this by upcycling dense models into MoEs however they often introduce parameter redundancy that degrades inference efficiency Alternatively standard layer pruning mitigates redundancy but inevitably compromises model accuracy To resolve this dilemma we propose Dense2MoE a novel framework that unifies pruning and upcycling through Layer Fusion UpCycling LF UC Guided by hardware Roofline theory Dense2MoE systematically overcomes the inference memory wall by pruning bandwidth heavy attention modules from redundant layers while repurposing their Multi Layer Perceptrons MLPs into MoE experts This structural innovation preserves the models core capabilities and strictly limits active parameters via selective token routing With a modest continual pre training budget Dense2MoE efficiently converts publicly available dense LLMs into on device ready MoE models Extensive experiments demonstrate that Dense2MoE significantly advances the Pareto frontier for on device inference latency versus model accuracy outperforming dense baselines state of the art compression and standard upcycling methods

Fengfa Li, Hongjin Ji, Yifeng Ding +2

Li Auto · The Chinese University of Hong Kong, Shenzhen

Mixture-of-Experts Pruning LLM Pruning On-Device Language Model Inference LLM Compression Mixture-of-Experts Inference

Ask PDF

May 22, 2026cs.AR

When NPUs Are Not Always Faster: A Stage-Level Analysis of Mobile LLM Inference

Deploying large language models (LLMs) on mobile devices increasingly relies on heterogeneous execution, yet no prior study has systematically characterized NPU effectiveness at the operator and pipeline level. We present the first stage-aware, multi-level benchmarking study of mobile LLM inference on a CPU-NPU heterogeneous SoC. We introduce an OPMASK-based controlled pipeline decomposition methodology that isolates communication, quantization, and computation overheads within the NPU execution path. Our results reveal a counter-intuitive stage-level performance reversal: CPUs outperform NPUs in the compute-intensive Prefill stage (up to 1.6x), while NPUs provide only limited acceleration in the memory-bound Decode stage (1.05-1.2x). We further show that scheduling overhead and cross-backend fallback reduce the practical benefits of NPU offloading. For the energy trend, increasing NPU offloading leads to higher energy consumption (up to 51%). Based on these findings, we derive design guidelines for NPU architects targeting on-device LLM inference.

Pu Li, Jiawen Qi, Qinyu Chen

Leiden Institute of Advanced Computer Science (LIACS), Leiden University, The Netherlands.

AI Accelerator Inference On-Device Language Model Inference LLM Inference Acceleration

Ask PDF

May 19, 2026cs.LG

Quant.npu: Enabling Efficient Mobile NPU Inference for on-device LLMs via Fully Static Quantization

Large language models (LLMs) are increasingly deployed on mobile devices, where Neural Processing Units (NPUs) necessitate fully static quantization for optimal inference efficiency. However, existing post-training quantization (PTQ) methods predominantly rely on dynamic activation quantization, rendering them incompatible with NPU hardware constraints. To bridge the gap between high-fidelity PTQ and NPU-constrained inference, we propose Quant.npu, a integer-only fully static quantization framework. It incorporates learnable quantization parameters and rotation matrices, enabling low-bit activation-weight quantization without runtime quantization parameters re-computation. Crucially, we identify that initialization and selective optimization of quantization parameters is pivotal for optimization stability, as improper initialization and naive joint optimization induce gradient instability that disrupts the optimization of rotation matrices. To address this, we propose a rotation-and-bit-width-aware initialization tailored to diverse activation profiles and a distribution-aware selective optimization (two-stage quantization pipeline) tailored to rotated and unrotated tensors. Furthermore, we introduce a sensitivity-guided adaptive mixed-precision scheme to balance accuracy with inference efficiency. Extensive experiments on real-world mobile NPUs demonstrate that Quant.npu achieves comparable accuracy to state-of-the-art methods, while reducing inference latency by up to 15.1%.

Jinghe Zhang, Daliang Xu, Chenghua Wang +5

Mixed-Precision Quantization LLM Quantization AI Accelerator Inference On-Device Language Model Inference Post-Training Quantization Neural Network Quantization

Ask PDF

May 17, 2026cs.LG

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models

Sub-billion-parameter Transformer language models are increasingly deployed on edge devices, where the privacy, latency, and operating-cost advantages of on-device inference are constrained by tight memory-bandwidth, energy, and thermal budgets that make architectural choice and accelerator-specific cost central to efficient inference. We present LLMForge, a hardware-aware neural architecture search (NAS) framework whose three composable contributions together make edge-LM architecture search hardware-conditioned, since different substrates impose different hardware cost bottlenecks. Infinite-Head Attention (IHA) decouples the number of query heads, KV groups, and per-head query/key and value dimensions, expanding the feasible per-layer attention configuration space by approximately 400x over grouped-query attention within our search-space ranges. Forge-Former, an encoder-based surrogate for ranking architectural candidates, outperforms MLP and random-forest baselines. Forge-DSE, an NSGA-II-based design-space-exploration engine, pairs Forge-Former with a multi-backend hardware cost model spanning GPUs, systolic accelerators, and ring-dataflow edge accelerators. Across four different hardware substrates, the searches converge to visibly different architectures whose shapes track each substrate's cost bottleneck. On the multi-chip ring substrate, our co-search returns three 300M-scale deployment-aware variants on the Pareto front. Each is re-trained on FineWeb-Edu-10BT under matched recipe against SmolLM2-360M and Qwen-0.5B architecture baselines. The accurate variant has the lowest validation loss 2.798 and competitive benchmark performance with fewer parameters, the energy-optimized variant lowers energy per token by 40%, and the latency-optimized variant lowers TTFT and TPOT by 43%.

Xinting Jiang, Junyi Luo, Ruichen Qi +4

Brown University · University of Michigan · Google Research

On-Device Language Model Inference Hardware-Aware NAS Attention Mechanisms Efficient Language Model Inference

Ask PDF

May 16, 2026cs.LG

OpenJarvis: Personal AI, On Personal Devices

Personal AI stacks, like OpenClaw and Hermes Agent, are becoming central to daily work, yet they route nearly every query (often over sensitive local data) to cloud-hosted frontier models. Replacing frontier models with local models inside existing stacks does not work: swapping Claude Opus 4.6 for Qwen3.5-9B drops accuracy by 25-39 pp across personal AI tasks like PinchBench and GAIA. Existing stacks bundle agentic prompts, tool descriptions, memory configuration, and runtime settings around a specific cloud model. Only the prompts can be tuned, and state-of-the-art prompt optimizers close just 5 pp of the local-cloud gap on their own. This motivates a decomposed personal AI stack: one that exposes individual primitives which can be optimized individually or jointly to close the local-cloud gap. We present OpenJarvis, an architecture that represents a personal AI system as a typed spec over five primitives: Intelligence, Engine, Agents, Tools & Memory, and Learning. Each primitive is an independently editable field, making the stack end-to-end optimizable and measurable against accuracy, cost, and latency. Towards closing the local-cloud gap without surrendering local-model properties, OpenJarvis introduces LLM-guided spec search, a local-cloud collaboration in which frontier cloud models propose edits across the spec at search time, only non-regressing edits are accepted, and the resulting spec runs entirely on-device at inference time. With LLM-guided spec search, on-device specs match or exceed cloud accuracy on 4 of 8 benchmarks and land within 3.2 pp of the best cloud baseline on average. They also reduce marginal API cost by ~800x and end-to-end latency by 4x.

Jon Saad-Falcon, Avanika Narayan, Robby Manihani +10

Stanford University · Lambda Labs

On-Device Language Model Inference LLM Agents Personal AI Agents

Ask PDF

May 16, 2026cs.LG

Lever: Speculative LLM Inference on Smartphones

Large language models (LLMs) are increasingly needed for interactive mobile applications, but high-quality models exceed the limited DRAM available on smartphones. Flash storage can hold larger models, yet flash-backed inference is slow because autoregressive decoding repeatedly invokes the target model and incurs costly I/O. We observe that speculative decoding is a natural fit for this setting: a small draft model can remain in DRAM, while a larger flash-resident target model verifies multiple candidate tokens per invocation. However, existing methods assume server-class accelerators and fail to account for prolonged I/O latency, limited computation parallelism, and irregular speculation execution. We present Lever, an end-to-end system for efficient flash-backed LLM inference on smartphones. Lever jointly optimizes the three stages of speculative decoding under mobile constraints. For drafting, it builds token trees using an I/O- and compute-aware gain-cost objective. For verification, it prunes low-value branches through early-exit prediction to reduce target-model computation. For execution, it maps speculation efficiently across mobile CPU-NPU hardware to improve utilization. Comprehensive evaluations show that Lever reduces inference latency by an average of 2.93x over baseline flash-offloaded inference and 1.50x over conventional speculative decoding, narrowing the latency gap between flash-backed and memory-resident LLM inference.

Tuowei Wang, Fengzu Li, Yanfan Sun +2

Tsinghua University · Beijing, China · Beihang University +1

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

Ask PDF

May 12, 2026cs.IT

CR^2: Cost-Aware Risk-Controlled Routing for Wireless Device-Edge LLM Inference

As large language models (LLMs) move from centralized clouds to mobile edge environments, efficient serving must balance latency, energy consumption, and accuracy under constrained device-edge resources. Query-level routing between lightweight on-device models and stronger edge models provides a flexible mechanism to navigate this trade-off. However, existing routers are designed for centralized cloud settings and optimize token-level costs, failing to capture the dynamic latency and energy overheads in wireless edge deployments. In this paper, we formulate mobile edge LLM routing as a deployment-constrained, cost-aware decision problem, and propose CR^2, a two-stage device-edge routing framework. CR^2 decouples a lightweight on-device margin gate from an edge-side utility selector for deferred queries. The margin gate operates on frozen query embeddings and a user-specified cost weight to predict whether local execution is utility-optimal relative to the best edge alternative under the target operating point. We further introduce a conformal risk control (CRC) calibration procedure that maps each operating point to an acceptance threshold, enabling explicit control of the marginal false-acceptance risk under the full-information utility reference. Experiments on the routing task show that CR^2 closely matches a full-information reference router using only device-side signals before deferral. Compared with strong query-level baselines, CR^2 consistently improves the deployable accuracy-cost Pareto frontier and reduces normalized deployment cost by up to 16.9% at matched accuracy.

Nan Xue, Shengkang Chen, Zhiyong Chen +4

Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai 200240, China · Department of Broadband Communication, Pengcheng Laboratory, Shenzhen 518000, China · Future Network of Intelligent Institute (FNii), the Chinese University of Hong Kong (Shenzhen), Shenzhen 518172, China +1

On-Device Language Model Inference LLM Inference Cost-Aware Inference Conformal Risk Control LLM Routing

Ask PDF

May 11, 2026cs.LG

CATS: Cascaded Adaptive Tree Speculation for Memory-Limited LLM Inference Acceleration

Auto-regressive decoding in Large Language Models (LLMs) is inherently memory-bound: every generation step requires loading the model weights and intermediate results from memory (e.g., High-Bandwidth Memory (HBM) for GPU servers), making throughput bottlenecked by memory bandwidth rather than compute. Speculative decoding addresses this by enabling parallel verification of multiple draft tokens, effectively amortizing the cost of each target-model call. However, existing speculative decoding methods are designed under the assumption that HBM is sufficiently large to hold both the target model and an auxiliary draft model simultaneously -- an assumption that breaks down on memory-constrained devices such as edge platforms with limited DRAM. We analyze the inference bottleneck in this memory-limited regime and propose CATS, a self-speculative decoding framework that conducts cascaded verification and correction based on the memory budget and parameter offloading patterns on memory-limited devices. This design maximizes token acceptance rate and end-to-end speedup while keeping the peak memory footprint on the device equal to that of the target model alone. We evaluate CATS on different models across five benchmarks on real edge devices. CATS can achieve a wall-clock speedup of up to 5.08x with no degradation in generation quality, outperforming the SOTA method by up to 1.45x under edge memory constraints.

Yuning Han, Yangchenchen Jin, Dylan Zhao +1

University of Florida Gainesville, FL 32611

On-Device Language Model Inference Memory-Efficient Inference Speculative Decoding LLM Inference Acceleration

Ask PDF

May 11, 2026cs.AI

Agent-X: Full Pipeline Acceleration of On-device AI Agents

LLM-based agents deliver state-of-the-art performance across tasks but incur high end-to-end latency on edge devices. We introduce Agent-X, a software-only, accuracy-preserving framework that accelerates both the prefill and decode stages of on-device agent workloads. Agent-X's two key components rewrite prompts to leverage prefix caching tailored to agent-specific input-token patterns and enable LLM-free speculative decoding for fast token generation with minimal overhead. On representative agentic workloads, Agent-X achieves a 1.61x end-to-end speedup in real systems with no accuracy loss and can be seamlessly integrated into existing on-device AI agents. To the best of our knowledge, ours is the first to systematically characterize and eliminate latency bottlenecks in on-device agents.

Jinha Chung, Byeongjun Shin, Jiin Kim +1

KAIST Republic of Korea, Daejeon

LLM Inference Efficiency On-Device Language Model Inference LLM Agent Workflow Optimization Prefix Caching LLM Agents

Ask PDF

May 11, 2026cs.NI

GELATO: Generative Entropy- and Lyapunov-based Adaptive Token Offloading for Device-Edge Speculative LLM Inference

The recent growth of on-device Large Language Model (LLM) inference has driven significant interest in device-edge collaborative LLM inference. As a promising architecture, Speculative Decoding (SD) is increasingly adopted where a lightweight draft model rapidly generates candidate tokens to be verified by a powerful target model. However, a fundamental challenge lies in achieving per-token resource scheduling to effectively adapt SD paradigm to resource-constrained edge environment. This paper proposes a Generative Entropy- and Lyapunov-based Adaptive Token Offloading framework, named GELATO, to maximize decoding throughput under energy constraints in a device-edge collaborative SD system. Specifically, an outer drift-plus-penalty loop makes online decisions to establish a reference drafting budget, managing long-term energy-throughput trade-off. Further, a nested entropy-driven generation mechanism executes early exiting to adapt to per-token dynamic generative uncertainty. Theoretical analysis establishes a rigorous performance bound on long-term throughput for GELATO. Extensive evaluations demonstrate that GELATO achieves a globally optimal tradeoff, outperforming state-of-the-art distributed SD architectures by 64.98% in token throughput and reducing energy consumption by 47.47% under resource-constrained environments, while preserving LLM decoding quality.

Zengzipeng Tang, Yuxuan Sun, Wei Chen +2

School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, China

On-Device Language Model Inference Edge Computing Speculative Decoding LLM Inference Acceleration

Ask PDF

May 9, 2026eess.SP

Large Language Models over Networks: Collaborative Intelligence under Resource Constraints

Large language models (LLMs) are transforming society, powering applications from smartphone assistants to autonomous driving. Yet cloud-based LLM services alone cannot serve a growing class of applications, including those operating under intermittent connectivity, sub-second latency budgets, data-residency constraints, or sustained high-volume inference. On-device deployment is in turn constrained by limited computation and memory. No single endpoint can deliver high-quality service across this spectrum. This article focuses on collaborative intelligence, a paradigm in which multiple independent LLMs distributed across device and cloud endpoints collaborate at the task level through natural language or structured messages. Such collaboration strives for superior response quality under heterogeneous resource constraints spanning computation, memory, communication, and cost across network tiers. We present collaborative inference along two complementary and composable dimensions: vertical device-cloud collaboration and horizontal multi-agent collaboration, which can be combined into hybrid topologies in practice. We then examine learning to collaborate, addressing the training of routing policies and the development of cooperative capabilities among LLMs. Finally, we identify open research challenges including scaling under resource heterogeneity and trustworthy collaborative intelligence.

Liangqi Yuan, Wenzhi Fang, Shiqiang Wang +2

L. Yuan, W. Fang, and C. G. Brinton are with Purdue University, IN, USA. · S. Wang is with University of Exeter, UK. · H. V. Poor is with Princeton University, USA.

LLM Inference Efficiency On-Device Language Model Inference LLM Inference LLM Routing Multi-LLM Collaboration

Ask PDF

May 4, 2026cs.RO

Benchmarking Local Language Models for Social Robots using Edge Devices

Social-educational robots designed for socially interactive pedagogical support, such as the Robot Study Companion (RSC), rely on responsive, privacy-preserving interaction despite severely limited compute. However, there is a gap in systematic benchmarking of language models for edge computing in pedagogical applications. This paper benchmarks 25 open-source language models for local deployment on edge hardware. We evaluate each model across three dimensions: inference efficiency (tokens per second, energy consumption), general knowledge (a six-category MMLU subset), and teaching effectiveness (LLM-rated pedagogical quality), validated against five independent human raters using the Raspberry Pi(RPi)4 as the primary platform, with additional comparisons on the RPi5 and a laptop GPU. Results reveal pronounced trade-offs: throughput and energy efficiency vary by over an order of magnitude across models, MMLU accuracy ranges from near-random to 57.2%, and teaching effectiveness does not correlate monotonically with either metric. Among the evaluated models, Granite4 Tiny Hybrid (7B) achieves a strong overall balance, reaching 2.5 tokens per second, 0.90 tokens per joule, and 54.6% MMLU accuracy; high MMLU accuracy does not appear necessary for strong teaching scores. Human validation on four representative models preserved the automated rank ordering (Pearson r = 0.967, n = 4). Based on these findings, we propose a three-tier local inference architecture for the RSC that balances responsiveness and accuracy on resource-constrained hardware.

Dorian Lamouille, Matevž B. Zorec, Farnaz Baksh +1

University of Tartu Tartu, Estonia · Institute of Computer Science University of Tartu Tartu, Estonia · Institute of Technology University of Tartu Tartu, Estonia

LLM Evaluation On-Device Language Model Inference AI in Education Small Language Models Robotics Social Robotics

Ask PDF

May 2, 2026cs.LG

Weight Pruning Amplifies Bias: A Multi-Method Study of Compressed LLMs for Edge AI

Weight pruning is widely advocated for deploying Large Language Models on resource-constrained IoT and edge devices, yet its impact on model fairness remains poorly understood. We conduct a controlled empirical study of three instruction-tuned models (Gemma-2-9b-it, Mistral-7B-Instruct-v0.3, Phi-3.5-mini-instruct) across three pruning methods (Random, Magnitude, Wanda) at four sparsity levels (10-70%) on 12,148 BBQ bias benchmark items with 5 random seeds, totaling 2,368,860 inference records. Our results reveal a Smart Pruning Paradox: activation-aware pruning (Wanda) preserves perplexity nearly perfectly (just 3.5% increase at 50% sparsity for Mistral-7B), yet produces the highest bias amplification, with Stereotype Reliance Score increasing 83.7% and 47-59% of previously unbiased items developing new stereotypical behaviors at 70% sparsity. Random pruning destroys language capability entirely (perplexity exceeding

10^4

and reaching

10^8

) but produces only random-chance bias. We further show that unstructured pruning provides zero storage savings and zero inference latency reduction on real edge hardware, undermining the primary motivation for its use in IoT deployment. Of 180 dense-vs-pruned comparisons, 141 (78.3%) are significant (

p < 0.05

) with mean

|h| = 0.305

. Published quantization studies report up to 21% of responses flipping between biased and unbiased states; our pruning results show transition rates nearly three times higher (47-59%), suggesting pruning poses a categorically greater risk to alignment than quantization. These findings demonstrate that perplexity-based evaluation provides false assurance of behavioral equivalence, and that IoT deployment pipelines require bias-aware validation before deploying pruned models at the edge.

Plawan Kumar Rath, Rahul Maliakkal

Momentum

Related topics

Latest papers 111