LLM Inference

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

30 papers in the last four weeks, up 233% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 187

Jul 17, 2026cs.LG

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching

Production LLM deployments combine two cost-reduction primitives: prompt caching (a discounted rate for re-used token prefixes) and prompt compression (fewer tokens sent). The compression literature has standardized on query-aware methods that produce a different compressed prefix per query, mechanically invalidating the prefix-strict cache on every call. We characterize this cost empirically on Anthropic's Sonnet 4.6 API and find caching is far from the rho=1.0 ideal the literature assumes: Sonnet's cache has a two-tier architecture with a sharp threshold near 3,500 tokens, below which the hit rate plateaus at rho~0.83 across 30-call sessions. Our cost model predicts, and experiments confirm, that under realistic rho, query-aware compression beats naive caching at high compression ratios (r>=6). We propose Cache-Aware Prompt Compression (CAPC), pairing query-agnostic compression with explicit cache_control plus a tier-preserving ratio bound that prevents over-compression from pushing the cached prefix into the hot tier. CAPC is the cheapest strategy in 16/16 configurations on LongBench-v2, with mean savings of 49% over cache-only, 64% over query-aware compression, and 90% over vanilla, at quality within 0.05 of the uncompressed baseline. We validate CAPC on three production workloads: an enterprise tool-using assistant with a 94k-token schema prefix (51.7% cost reduction at r=3); a graphify knowledge-graph RAG pipeline across two codebases (9.3x vs cache-all on FastAPI, 2.4x on httpx); and the public tau-bench retail benchmark (50 tasks), where CAPC is the cheapest of four strategies with reward exactly equal to vanilla (both 36/50, p=1.00) while query-aware compression is the most expensive at +40.1% over vanilla -- the first production confirmation of the crossover model's negative-ROI prediction on a public benchmark.

Yan Song

PayPal Inc.

LLM Serving LLM Inference Cost-Aware Inference Prefix Caching Prompt Compression

Jul 15, 2026cs.DC

The Cost and Network Limits of Space-Based AI Compute

This paper evaluates whether large-scale AI data centers deployed in low-Earth orbit (LEO) could become a cost-effective alternative to terrestrial facilities. The analysis compares orbital and ground-based systems across launch cost, power generation, cooling, radiation exposure, and atmospheric reentry, as well as compute-network performance. A key distinction is the shift from terrestrial Clos networks to space-based mesh networks using laser inter-satellite links. Using bisection bandwidth, bisection intensity, and roofline-style models, we show that while LEO-based inference may be feasible, training frontier-scale LLMs in orbit is unlikely to be competitive with terrestrial data centers.

Kees van Berkel

Technical University Eindhoven, Dept. of Math. & Computer Science P.O. Box 513, 5600 MB Eindhoven, The Netherlands

LLM Inference Cost-Aware Inference LEO Satellite Networks LLM Training

Jul 14, 2026cs.MA

Automatic Model-Hardware Co-Adaptation for Heterogeneous AI Accelerators

Large language models now evolve faster than production inference systems can be ported and optimized. New releases change attention, MoE routing, quantization formats, KV-cache layout, and parallel execution patterns, while deployed accelerator fleets remain heterogeneous across hardware generations, framework forks, operator libraries, compiler backends, and communication runtimes. Serving a new model on existing hardware is therefore a model-framework-kernel-hardware co-adaptation problem. We present MetaInfer, an LLM-agent system that formulates inference adaptation as route search over a costed execution-adaptation graph. The graph connects model semantics, framework dispatch, kernel choices, hardware capabilities, runtime evidence, and serving objectives. MetaInfer constructs and updates this graph during execution, restores missing or blocked routes through patches, and reduces route cost through staged validation and end-to-end profiling. Three real episodes -- DeepSeek V4 Flash on NVIDIA A800, GLM 5.3 Flash on NVIDIA A800, and DeepSeek V4 Flash on Hygon K100AI DCU -- demonstrate deployment repair, cross-model knowledge transfer, and portability across heterogeneous accelerator software stacks.

Tian Chen, Mingheng Mi, Pu Wang +2

Pazhou Laboratory (Huangpu) · Unaffiliated

AI Accelerator Inference LLM Inference LLM Inference Serving Hardware-Software Co-Design

Jul 14, 2026cs.CR

Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models

On-device LLM inference faces a trilemma of response latency, limited hardware resources and user privacy. Full cloud inference delivers strong computing power but exposes user prompts and dialogue data, while standalone on-device inference is unfeasible for most consumer and embedded edge devices. This paper presents a privacy-centric edge-cloud collaborative LLM inference framework built on endpoint-authenticated KV cache. Local endpoints handle input preprocessing, embedding computation, adaptive feature optimization, KV cache authentication, speculative decoding and low-dimensional model head calculation, while the cloud conducts authenticated decoder inference, KV cache management, token verification and high-dimensional vocabulary projection. Endpoints fuse partial outputs, apply language-adaptive masking and sample target tokens. All transmitted data and truncated logits are quantized and AES-GCM encrypted for privacy, with core lightweight modules, draft parameters and cache access policies kept local to avoid leakage. The framework supports heterogeneous devices including CPU-only, GPU-equipped and embedded devices via optimized streaming, batching and quantized ONNX deployment. Evaluations demonstrate that the framework reduces per-token latency by up to 46.1% and downlink payloads by up to 67.4% over baseline split inference, retaining comparable performance to full cloud inference.

Yi Li, Chen Li, Jiexiong Liu

KunlunMeta

On-Device Language Model Inference Privacy-Preserving Language Models LLM Inference Efficient Language Model Inference

Jul 13, 2026cs.LG

FastTPS: An Optimized Method for LLM Token Phase for AI accelerators

The popularity of large language models (LLMs) escalates an ongoing demand for effective inference. However, due to the sequential processing of tokens during the token phase in decoder-only LLMs inference, the inherent low parallelism leads to reduced throughput and suboptimal utilization of the computing units on artificial intelligence (AI) accelerators, particularly when handling long-sequence inputs that impose significant memory overhead. Recently, many reported methods have been developed as potential solutions, since they emerge with numeric deviation. This paper presents FastTPS, a high performance and low-precision loss method for accelerating the token-phase in LLM inference on general AI accelerators which includes three key components: (1) AI accelerator-enabled reloading-free KV Cache concatenation which decreases memory access overhead as well as enables full fusion of Attention, (2) high-efficiency and high-accuracy 'RoPE' attention based on the tiling optimized FLAT, and (3) highly-fused MLP with fine-grain pipeline scheduling. Our results confirm that FastTPS significantly alleviates memory bottlenecks in the token phase, delivering a 6x speed improvement (compared to none-fusion) on an AMD Ryzen AI 300 series NPU with BF16 precision while sustaining 93% peak memory bandwidth utilization during Phi3-mini-4k-instruct inference.

Wenzong Yang, Danyang Zhang, Kun Cao +17

Advanced Micro Devices, Inc., Santa Clara, California, USA.

AI Accelerator Inference LLM Inference KV-Cache Management LLM Inference Acceleration Efficient Attention

Jul 13, 2026cs.CL

Amplitude-Only FFN Intervention for Tool-Structured LLM Inference Method: Gated Evaluation Protocol, and Cross-Model Empirical Results

Large language models increasingly operate as tool-using agents, where small format, argument, or function-call errors can invalidate otherwise plausible responses. We study inference-time feed-forward network (FFN) intervention for improving structured outputs without retraining model weights. Our project began with Orthogonal Residual Projection (ORP), a direction-changing repair attempt that revealed sensitive SwiGLU FFN intervention sites but often caused more harm than fixes. We therefore propose Amplitude Gating (AG), a non-destructive alternative that preserves pretrained FFN weight directions and modulates only activation magnitudes during generation. We define a fine-grained intervention system spanning P1/P2/P3 and branch-specific P1s/P2a/P2b sites, and introduce an evaluation protocol that separates combination-oracle headroom from fixed configurations and learned gates, enforces sample-level accounting, and uses task-aware metrics for binary and partial-credit datasets. Across Qwen3.5-9B, Qwen3-8B, and Qwen2.5-7B, AG is weakly positive in aggregate but strongest on tool-structured tasks. On Qwen3.5-9B, a category-level learned gate improves tool/structured/agentic performance from 38.66% to 42.92% (+4.27 percentage points), with Hermes function-call tasks reaching about +7.6 points. On Qwen3-8B, Hermes JSON mode improves by +11.36 points. Qwen2.5-7B retains oracle headroom but current learned gates fail to capture it, showing that deployment requires model- and category-specific routing. Comparisons of entropy AG with Newton-Schulz-windowed AG show that neither family is uniformly dominant. These results identify tool-structured inference as the most credible first target for safe FFN-level inference optimization, while prospective online validation and broader cross-model evaluation remain necessary.

Sheng Xu, Junhua Wang, Boyuan Huang +3

Alibaba Cloud

LLM Inference LLM Tool Use Structured Output Generation Causal Interventions in Language Models

Jul 10, 2026cs.SE

Attention to Detail: Evaluating Energy, Performance, and Accuracy Trade-offs Across vLLM Configurations

Large Language Models are reshaping how software is developed and maintained. They are typically deployed in production using inference engines such as vLLM, which can efficiently serve pre-trained, highly configurable models. While prior work has focused on model architectures and hardware acceleration, the impact of inference engine configuration on energy consumption, performance, and output quality remains poorly understood. In this paper, we present a large-scale controlled study of three selected vLLM configuration options: attention kernel type, prefix caching, and chunked prefill. We evaluate all combinations of these configurations across 5 open-weight LLMs and 5 diverse inference tasks, totaling

9,000

runs and

93,600

measures. We analyze energy consumption, latency, and accuracy, and examine both main effects and interaction effects between configuration options and tasks. Our results show that the studied configuration options significantly impact energy and performance, mainly driven by attention type and prefix caching, while chunked prefill has a limited effect under the default vLLM serving configuration and evaluated workloads. These effects are highly model- and workload-dependent, and no configuration is universally optimal. We further show that model choice dominates global trade-offs, while configuration tuning provides local improvements along the Pareto frontier. Unexpectedly, inference options can also affect model accuracy.

Nada Zine, Tristan Coignion, Vincenzo Stoico +3

Univ. Lille, CNRS, Inria · Univ. Bordeaux, CNRS, LaBRI · Vrije Universiteit Amsterdam +1

LLM Inference Efficiency LLM Evaluation LLM Serving LLM Inference

Jul 9, 2026cs.LG

Gauge dependence and structured-output corruption in sign-branched repetition penalties: measurements across models, inference stacks, and alternative repetition controls

The multiplicative repetition penalty shipped across the LLM inference ecosystem (HuggingFace, vLLM, llama

.

cpp, and a dozen further engines) branches on the sign of each raw logit (divide positives by theta, multiply negatives). But the softmax is unchanged by adding a constant to every logit, so a model's logit zero-point is arbitrary (a gauge choice), and the sign-branch reads it. Two measurable consequences follow. (1) The penalty is not well-defined: re-centering a model's logits by a constant is a provable no-op at theta=1, yet at a routine theta=1.3 it changes 58-96% of greedy tokens, while subtractive and normalized penalties change none; real checkpoints sit at widely different zero-points, so a fixed repetition_penalty is a different operation on every model. (2) It corrupts structured output: on 200 real-world JSON schemas, theta=1.3 drops the rate of valid, schema-conformant output from 97% to 23%. Applying the penalty to normalized log-probabilities instead of raw logits removes the gauge dependence by construction; HuggingFace's beam search has applied its processor chain, penalty included, to log-probabilities since at least v4.0.0, so repetition_penalty already names two different operators depending on decoding strategy. Because equal theta is not equal strength across the two operators, we also compare them at matched suppression, calibrated per model by search: there the normalized operator is statistically no worse on any quality metric measured, but on four of seven models it cannot match the raw operator's suppression at theta >= 1.15, and on six of seven at theta=1.3, the setting where the corruption was measured. This note gives the mechanism, the measurements (five models up to 7B; two code models; both effects replicated inside vLLM and llama

.

cpp through their own samplers), the per-model calibration map, and the normalized variant.

Peter Hollows

Language Model Decoding LLM Inference LLM Reliability

Jul 6, 2026cs.DC

When Words Predict Workload

Standard distributed \ac{llm} schedulers rely on static token counts or rolling latency averages, making them susceptible to failures on statutorily constrained text. On \ac{epo} claims governed by Article 84 \ac{epc}, linguistic rigidity makes human and machine authorship statistically indistinguishable. Resolving this ambiguity mid-flight forces dynamic multi-model ensemble expansion, triggering unpredictable KV-cache and weight-allocation spikes that saturate consumer-grade edge GPU VRAM and cause severe \ac{oom} crashes. To prevent hardware collapse, we propose a CPU-side Linguistic Resource Forecasting (LRF) gateway. The gateway extracts a 16-dimensional text-structure vector and applies an XGBoost predictor to forecast trap-band membership. The resulting escalation probability (

\Pesc

) is evaluated against a dynamic, closed-form routing threshold (

\Tauroute(t)

) computed via real-time latency telemetry. Requests are safely routed to either a local Qwen2.5-7B edge worker or a remote contrastive ensemble (Qwen2.5 7B + 32B) on an NVIDIA H100 \emph{before} any edge GPU memory is allocated. In a 6,000-request live trial, the LRF gateway reduced the operational misroute fraction (

R_{\mathrm{mis}}

) to

0.087

--

0.095

, an order of magnitude below the token-count baseline (

0.849

). Peak edge VRAM remained safely bounded at

\SI{4.82}{\gibi\byte}

(under the

\SI{8}{\gibi\byte}

ceiling) across a

27\times

variation in \ac{wan} delay. The predictor achieved a live-trial AUROC of

0.84

, and the dynamic

\Tauroute(t)

controller yielded an

8.2\%

relative reduction in misroutes compared to an equivalent static threshold.

Anubhab Banerjee

Nokia Germany

On-Device Language Model Inference LLM Inference Real-Time Scheduling LLM Inference Scheduling LLM Routing LLM Request Scheduling

Jul 6, 2026cs.AR

Is Your NPU Ready for LLMs? Dissecting the Hidden Efficiency Bottlenecks in Mobile LLM Inference

Deploying Large Language Models (LLMs) on mobile devices enhances privacy and reduces latency, but is severely bottlenecked by hardware inefficiency. We present the first comprehensive, cross-layer measurement study of mobile LLM inference, uniquely spanning five mainstream frameworks (e.g., llama.cpp, GENIE) and three hardware backends (CPU, GPU, NPU). To enable this analysis, we develop PowerBench, a fine-grained profiling tool that provides the first backend-specific energy attribution, moving beyond traditional device-level measurements. Our study yields three critical insights: (1) Framework-induced performance gaps are substantially amplified on NPUs, reaching up to 10x using custom operators due to divergent offloading and quantization strategies. (2) We identify a distinct phase split where NPUs excel at compute-bound prefilling, while CPUs outperform all other backends in memory-bound decoding. This is driven by the NPU's preference for large, fixed-shape workloads, which conflicts with the small-kernel, dynamic nature of decoding. (3) Backend-specific profiling uncovers substantial scheduling headroom missed by prior work. Suboptimal thread configurations, uncoordinated NPU sleep latencies, and CPU polling intervals result in up to 40% energy waste. Leveraging these findings, we present an energy-oriented best-practice configuration for mobile LLM inference. We estimate that this configuration could reduce energy consumption by up to 54.8% on the NPU backend across three datasets.

Guanyu Cai, Ruiming Tian, Lang Yang +4

Tsinghua University · Beijing Jiaotong University

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

Jul 6, 2026cs.AI

Heaviside Continuity of Rolling Coefficients for Eliminating Epistemic Entropy in Large Language Models

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

MY Pitsane, Hope Mogale

North-West University, RSA · Mankind Research Labs, Sandton · University of Pretoria, RSA

LLM Answer Verification LLM Inference LLM Reliability

Jul 4, 2026cs.LG

Knowing When to Stop: Predicting Execution-Consistency Convergence in Text-to-SQL

Repeated LLM calls are the standard way to estimate how trustworthy a Text-to-SQL result is: run the pipeline multiple times, judge each SQL execution, and use the consistency of the verdicts as a confidence signal. The open question is when to stop, when the consistency has converged. We formulate this as a convergence-prediction problem and train a family of lightweight 1-D models that observe the running consistency trajectory and decide, at each step, whether further runs are unlikely to shift it materially, and we benchmark them against a principled Beta-Bernoulli stopping rule and a learned run-count baseline. On the BIRD benchmark and two production customer datasets, our method adapts its stopping point to each user question, halting sooner when consistency converges early and continuing longer when it converges late. We further show that the weak serial correlation between runs lets us permute their order as a training augmentation, controlled by a tunable shuffling weight. Performance stays consistent across the three datasets, and to mimic an imperfect production judge we inject noise into the correct/incorrect verdicts obtained by comparing the generated and ground-truth SQL results, showing that the method still predicts convergence reliably.

Yaron Anavi, Mor Aisenberg, Nadav Nesher +2

GIGASPACES

LLM Inference Efficiency LLM Inference Text-to-SQL LLM Reliability

Jul 2, 2026cs.DC

WattGPU: Predicting Inference Power and Latency on Unseen GPUs and LLMs

Large Language Model (LLM) inference workloads are a rapidly growing contributor to data center energy consumption. Optimizing these deployments requires matching specific LLMs to the most efficient GPUs, but operators currently lack the tools to do so without exhaustively profiling each combination. While some predictive models exist, they still require profiling data and struggle to generalize to hardware unseen during training. To address this, we introduce \textit{WattGPU}, featuring two predictive models for mean GPU power draw and Inter-Token Latency (ITL). Our approach leverages only publicly available LLM metadata and GPU specifications, eliminating the need for hardware access or profiling while enabling generalization to unseen NVIDIA server-grade GPUs and LLMs. We evaluate our models using rigorous leave-one-GPU-out and leave-one-LLM-out cross-validation on a dataset of 42 open-source LLMs (0.1B--27B parameters) and 8 GPUs under both offline and server scenarios. The mean power draw model achieves a median absolute percentage error of

\leq3.4\%

for offline and

\leq13.5\%

for server scenarios on unseen GPUs, while the latency model achieves

\leq8.5\%

in server mode, both maintaining strong GPU ranking correlations for server scenarios (Kendall

τ\geq0.76

). Compared to standard physically grounded baselines -- Load-Scaled Thermal Design Power (TDP) for power draw and roofline for latency -- our models reduce median absolute percentage error by approximately 4

\times

on unseen LLM-GPU combinations for server scenarios or approximately 2

\times

for completely unseen GPUs. WattGPU's data and code are publicly available at https://github.com/maufadel/wattgpu.

Mauricio Fadel Argerich, Jonathan Fürst, Marta Patiño-Martínez

Universidad Politécnica de Madrid, C. de los Ciruelos, 28660 Boadilla del Monte, Madrid, Spain · Zurich University of Applied Sciences, Gertrudstrasse 15, 8400 Winterthur, Switzerland

LLM Inference Efficiency Energy-Efficient ML LLM Inference

Jul 2, 2026cs.DC

Lynx: Progressive Speculative Quantization for accelerating KV Transfer in Long-Context Inference

Long-context inference is increasingly common in large language model (LLM) serving, driven by retrieval-augmented generation and agentic systems. In disaggregated inference, these workloads require transferring large Key-Value (KV) caches across the network, where decoding cannot begin until the transfer completes. Recent KV quantization techniques reduce data volume and alleviate this bottleneck, but existing schemes fail to achieve both low network-exposed latency and high inference accuracy. We challenge the assumption that the KV cache is an indivisible unit that must be fully received before use. We leverage the observation that different bits in the KV cache contribute unequally to attention computation and inference precision: the most significant bits capture the coarse structure of attention and the least significant bits refine precision. This property enables partial use of the KV cache during decoding. We present Lynx, a system that enables progressive, split-stream KV transfer by partitioning the KV cache into a high-priority Anchor stream carrying the most significant bits and a low-priority Residual stream carrying remaining precision. Decoding begins upon receipt of the Anchor stream and proceeds speculatively while the Residual stream is transferred concurrently, followed by verification that ensures equivalence to higher-precision decoding. Across multiple models and serving workloads, Lynx achieves Time-to-First-Token (TTFT) comparable to aggressive 4-bit KV quantization, while matching the accuracy of high-precision (BF16) inference, improving TTFT over standard 8-bit KV quantization by up to

1.43\times

and improving accuracy over state-of-the-art by up to

5.1\%

.

Wenchen Han, Gingfung Matthew Yeung, Marco Barletta +3

University College London · Huawei

LLM Inference KV Caching Long-Context Language Model Inference KV-Cache Management LLM Inference Acceleration KV-Cache Quantization

Jul 1, 2026cs.CL

Dynamic Bidirectional Pattern Memory: A Production-Scale Empirical Characterisation of Inference-Time Gating in Clinical NLP

We study inference-time pattern-memory gating in a production-scale clinical natural language processing (NLP) pipeline. The pipeline pairs a generator (Llama-3.3 70B) proposing extractions with a verifier (MMed-Llama-3.1 70B) accepting or rejecting them, over 167,034 PMC-Patients narratives, and adds a lightweight memory that learns at deployment which extractions to filter, so the verifier need not re-examine candidates already seen to fail. We report four findings. First, learning filtering rules directly from the verifier's rejections failed at full scale: the relation-extraction filter stayed empty despite 785,797 logged rejections, because they were spread too thinly across too many distinct forms to accumulate. Second, a simpler rule using a fixed clinical ontology produced the same filtering without the verifier, capturing 49,734 ontology-violating relations on a held-out 5,000-patient set. Third, of five versions of the question-answering filter, four failed for distinct, instructive reasons; the fifth succeeded by checking whether a patient's extracted entities support the question asked, and where it applies was 1.84 times likelier to flag an answer the verifier would reject than one it would accept. Fourth, one pattern held across all five: a filter is selective only when it tests the same evidence the verifier weighs, not when it imitates the verifier's output. Together these give a transferable result for any generator-verifier pipeline: the most natural memory design can fail silently at scale, and whether a pre-generation gate is selective is decided before any engineering effort, by whether its signal probes the question the verifier itself answers. Throughout, the system flags suspect extractions rather than deleting them, so every decision stays visible for clinical review. All code and test artefacts are released openly.

Ali H. Lazem, William Teahan

School of Computer Science and Engineering, Bangor University, Bangor, Gwynedd, LL57 2DG, United Kingdom · University of Thi-Qar, Nasiriyah, 64001, Iraq

LLM Inference Clinical Information Extraction Clinical NLP

Jun 26, 2026cs.PF

KernelSight-LM: A Kernel-Level LLM Inference Simulator

As large language models (LLMs) move into production serving, practitioners must rapidly evaluate inference performance across diverse hardware, models, and serving parameters to meet cost and latency targets. However, the end-to-end behavior of LLMs couples serving-layer policies with low-level GPU kernel execution and rapidly evolving architectures, forcing slow, deployment-specific benchmarking that is hard to generalize. We present KernelSight-LM, a fine-grained inference simulator that models token-level execution and produces kernel-level latency breakdowns. It decomposes each serving step into a roofline kernel model with a learned efficiency term, a communication model, and a host-overhead model, composed through a discrete-event scheduler that also captures mechanisms like prefix caching and continuous batching. KernelSight-LM offers two prediction tiers that trade target-GPU data for accuracy. The cross-generation tier uses no target-GPU measurements, only hardware specifications and kernel microbenchmarks from previously profiled GPUs, and predicts per-kernel latency on an unseen GPU generation to 12.1% error, a 1.8x improvement over the roofline baseline (22.0%). A second target-measured tier adds one model-agnostic kernel-microbenchmark sweep on the target GPU, sharpening per-kernel error to 3.8%, a 7.3x improvement over a comparable baseline (27.7%). Both tiers require far less target-GPU data than the prior systems they extend. In our simulator, these predictions yield end-to-end median (p50) errors across six model families of 15.4%, 12.8%, and 3.0% (TTFT, TPOT, throughput) in the cross-generation tier and 14.3%, 6.2%, and 2.7% in the target-measured tier, matching dedicated profiling tools while collecting far less on-device data. Beyond prediction, its kernel-level bottleneck breakdowns support hardware/software co-design and capacity planning.

Xiteng Yao, Taeho Kim, Hengzhi Pei +7

Amazon Web Services Santa Clara, CA, USA · Boston University Boston, MA, USA

LLM Inference LLM Inference Serving

Jun 26, 2026cs.IR

End-to-End Dynamic Sparsity for Resource-Adaptive LLM Inference

Large Language Models (LLMs) inference is typically deployed under a static resource assumption, where models execute a fixed computational graph regardless of the runtime environment. However, real-world cloud infrastructure is inherently dynamic, characterized by fluctuating availability (e.g., spot instance preemption) and tiered Quality-of-Service requirements. In such volatile settings, static models are inflexible: they either crash under resource constraints or waste compute on redundant operations. To bridge this gap, we propose Learning to Allocate (L2A), an end-to-end framework for resource-adaptive inference. Unlike prior methods that condition only on input difficulty, we formulate inference as a constrained allocation problem conditioned on both the input and the runtime resource budget itself. We introduce lightweight, budget-conditioned and input-aware gating networks integrated into the LLM. These gates are trained via a unified objective that jointly optimizes task performance, logical consistency, and resource costs along three axes matching how real-world dynamics manifest: layer skipping for memory and depth pressure, head pruning for throughput contention, and reasoning-token reduction for latency tightening. This lets the model learn a budget-aware policy beyond input difficulty alone: it adaptively configures its computational footprint with respect to real-time resource dynamics, maximizing reasoning depth when resources permit while enforcing strict frugality when budgets tighten. A single L2A model traces the entire compute-accuracy Pareto frontier on Llama-3-8B and Qwen-3-4B: at up to 34% realized layer sparsity, it stays within 0.6% of the dense baseline on GSM8K, with the same gap holding zero-shot on out-of-distribution tasks, while every static or heuristic baseline requires a separately tuned model and still drops by 5-10% at comparable inference time.

Yuhang Chen, Jinhao Duan, Ruichen Zhang +11

University of North Carolina at Chapel Hill · Meta AI

LLM Inference Structured Sparsity LLM Inference Acceleration Inference-Time Compute Allocation Sparse Neural Networks Conditional Computation

Jun 23, 2026cs.LG

Reasoning as Attractor Dynamics: Latent Memory Retrieval via Gibbs-Weighted Energy Minimization

Large Language Models (LLMs) are traditionally viewed as autoregressive generators. However, from the perspective of collective computation, they function as high-dimensional Dense Associative Memories that store complex reasoning patterns as latent attractors. In this work, we investigate the energy landscape of mathematical reasoning. We posit that correct reasoning chains correspond to deep, wide attractor basins ("flat minima") in the model's output distribution, whereas hallucinations manifest as sharp, unstable local minima. To exploit this geometry, we introduce a retrieval mechanism based on a Gibbs measure of the trajectory's spectral entropy. By sampling multiple reasoning paths and weighting them by their inverse energy (

P \propto e^{-βE}

), we approximate the equilibrium distribution of the associative memory, effectively ``relaxing'' the system into a robust solution. Empirically, this physics-inspired mechanism improves Microsoft Phi-3.5 performance on GSM8K by 5.38% (84.7%

\to

90.1%), demonstrating that inference is better modeled as a dynamic settling process into an attractor basin rather than greedy next-token prediction.

Kanishk Awadhiya

Independent Researcher

LLM Inference Representation Geometry in Language Models LLM Reasoning

Jun 23, 2026cs.CL

The African Language Tax: Quantifying the Cost, Latency, and Context Penalty of Tokenizing African Languages in Frontier LLMs

Commercial large language models bill, scale latency, and budget context per token. Yet tokenizers assign more subword tokens to the same meaning in some languages than in others, so speakers of languages with high token-fertility pay a structural penalty before a model is ever invoked. This penalty is documented for multilingual settings in general, but it has not been measured systematically for African languages at the level of enterprise deployment economics and cognitive context capacity. We measure it across 20 African languages spanning five language families and three scripts (Latin, Ge'ez/Ethiopic, N'Ko; 19 appear in the primary FLORES-200+ corpus, with Nigerian Pidgin measured via MAFAND-MT only), using parallel corpora so that the language effect is isolated from content. Across 11 frontier and open tokenizers on FLORES-200+, every African language carries a tokenization premium above English (median 1.88x on GPT-5 / o200k_base, up to 8.92x for N'Ko); the penalty is largest for Ethiopic and N'Ko scripts (reaching 7-9x) and is near-invariant across corpora (FLORES vs SIB-200 Pearson r = 0.9998). Translated into deployment terms, this results in up to 8.9x inference cost and an equivalent generation-latency multiplier (N'Ko vs English on GPT-5; 7.4x for Amharic), and as little as 11% of English's effective context window. The best currently available tokenizer for African languages, Gemma 4, reduces the mean premium from 3.31x (cl100k_base) to 2.38x, but no tokenizer eliminates the penalty. We release an open measurement tool (afri-fertility), a public leaderboard, a results dataset, and mitigation guidance for African builders. The penalty falls hardest on the languages whose speakers can least afford it, a digital divide encoded directly into the subword vocabulary.

Olaoye Anthony Somide

DataLens Africa Research · CipherSense AI Technologies Ltd.

Multilingual Language Models Multilingual Language Model Evaluation LLM Inference Low-Resource Language Processing

Jun 22, 2026cs.DC

Concordia: JIT-Compiled Persistent-Kernel Checkpointing for Fault-Tolerant LLM Inference

Long-running LLM agents keep valuable state resident on GPUs: KV caches, request schedulers, communication state, and sometimes online adapters. Losing this state after a GPU or communicator failure can discard minutes to hours of work, yet existing recovery mechanisms either restart the whole serving stack or require application-specific checkpoint logic inside every attention and runtime component. This paper argues that fault tolerance for such workloads needs a GPU-resident execution context: checkpoint hooks must run at device synchronization points, observe binary kernels that frameworks and libraries actually execute, and recover without putting the host CPU on the critical path. We present Concordia, a runtime that uses a device-resident persistent kernel as the substrate for fault-tolerant LLM inference. Concordia interposes on GPU module loading and supports PTX- and SASS-level instrumentation, allowing checkpoint and pause hooks to be inserted below framework code and library boundaries. For each registered LLM state region, Concordia JIT-compiles a specialized delta-checkpoint handler -- for example, a KV-block scanner, adapter-page scanner, or recovery applier -- and hot-swaps it into the persistent kernel's operator table. The persistent kernel consumes a lock-free ring buffer of compute, checkpoint, append-log, and recovery tasks, so the same always-on executor triggers dirty-page detection, stages deltas, and appends committed records to a CPU-visible log in CXL memory or host DRAM.

Yuhang Gan, Yiwei Yang, Yuyi Li +6

University of California Santa Cruz USA · UC Santa Cruz USA · University of California, Davis USA +2

Jun 22, 2026cs.LG

GRINQH: Graded Input-based Quantization Hierarchy for Efficient LLM Generation

Autoregressive decoding with LLMs is primarily bottlenecked by GPU memory bandwidth, especially in edge-computing settings. While quantization is essential for mitigating this bottleneck, most existing methods treat inference as a uniform process and fail to account for the asymmetry between the compute-bound prefill stage and the memory-bound decoding stage. We propose GRINQH (GRaded INput-based Quantization Hierarchy), a weight-only post-training quantization framework that accelerates decoding by unifying quantization and sparsification. GRINQH leverages activation magnitudes as a proxy for computational importance to dynamically assign weight channels to different precision levels, enabling flexible average bit widths during decoding. Evaluated on Llama3 and Qwen3 models, GRINQH outperforms state-of-the-art fixed- and mixed-precision baselines at comparable 3- and 4-bit settings, even enabling effective 2-bit generation. We experimentally verify theoretical speedups by leveraging a hierarchical nested memory layout for multi-precision storage in a custom GPU kernel. Ultimately, GRINQH establishes a new state-of-the-art Pareto frontier for LLM generation, enabling a dynamic trade-off between generation quality and inference speed.

Jette Oberländer, Jan Finkbeiner, Catherine M. Schöfmann +1

Fakultät für Informatik, RWTH Aachen, Aachen, 52074, Germany · Peter Grünberg Institut, Forschungszentrum Jülich GmbH, Jülich, 52425, Germany · Fakultät für Elektrotechnik und Informationstechnik, RWTH Aachen, Aachen, 52062, Germany

Mixed-Precision Quantization LLM Quantization LLM Inference LLM Inference Acceleration Weight-Only Quantization Post-Training Quantization

Jun 22, 2026cs.AI

Abstract representational geometry supports inference in large language models

A defining feature of human intelligence is the ability to adapt to changing environments by inferring latent task structure from sparse observations. Neuroscientific research indicates that this capability relies on the hippocampus constructing abstract representations, expressed as low-dimensional, approximately orthogonal manifolds in neural state space. However, the internal mechanisms of large language models (LLMs) remain largely opaque, making it unclear whether they form comparable abstract representations or instead rely on task-specific statistical regularities when performing comparable reasoning tasks. Here we adapt a contextual reversal-learning paradigm to a text-based setting and compare humans and LLMs at both the Behavioural and representational levels. We report that although LLMs exhibit generalizable reasoning less frequently than humans, when such inference occurs, their internal states exhibit abstract geometric structures that resemble those reported in the hippocampus. Notably, this representational geometry is not uniformly distributed but is organized hierarchically across model depth: whereas lower layers show early, stable encoding of stimulus identity, higher layers form a hippocampal-like functional band enriched for abstract context geometry associated with inference. Furthermore, complementary intervention experiments mechanistically implicate geometry in reasoning: task-sequence language modelling induces geometric disentanglement, whereas geometric regularization of higher layers increases the emergence of generalizable inference. Together, these findings establish abstract representational geometry as a mechanistic principle supporting inference in large language models.

Yunan Zeng, Yuwang Wang

College of Future Information Technology, Fudan University, Shanghai, 200433, China · Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, 100084, China

LLM Inference LLM Interpretability Representation Geometry in Language Models

Jun 19, 2026cs.LG

Depth-Entropy Guided Sampling for Training-Free LLM Reasoning

Reinforcement learning (RL) has become the dominant paradigm for improving the reasoning capabilities of large language models, but it requires expensive training, curated data, and reward signals. Recent work shows that sampling from sharpened base-model distributions at test time recovers much of the RL gain, yet existing methods rely solely on output-layer likelihoods and ignore the transformer's internal forward-pass dynamics. We introduce Depth-Entropy Guided Sampling (DEGS), a training-free, test-time method that exploits layer-wise entropy collapse as an intrinsic quality signal. We observe that stronger reasoners -- including RL-posttrained variants -- exhibit a distinctive "late collapse": logit-lens decoded entropy stays elevated until deeper layers before converging. We define a per-sequence collapse depth

D(\mathbf{x})

and a joint objective

π(\mathbf{x}) \propto p(\mathbf{x})^α\exp(βD(\mathbf{x}))

that combines sequence likelihood with this depth-entropy structure, instantiated inside an MCMC power-sampling framework (DEGS-MCMC). Across three open-weight models and four reasoning benchmarks, this near-chance per-candidate signal compounds over the sampling trajectory into state-of-the-art training-free accuracy, with gains largest out of domain and on the harder splits -- exactly where likelihood alone falls short -- at single-digit-percent wall-clock overhead. DEGS narrowly trails an in-house GRPO reference on the math splits GRPO was trained for, yet surpasses it out of domain on GPQA for all three models, without any training, reward model, or labeled data.

Zibin Meng, Peng Xie, Kani Chen

1The Hong Kong University of Science and Technology

LLM Inference Test-Time Scaling LLM Reasoning

Jun 19, 2026cs.LG

Demystifying Numerical Instability in LLM Inference: Achieving Reproducible Inference for Mission-Critical Tasks with HEAL

As Large Language Models (LLMs) deploy into mission-critical domains (e.g., finance, medicine, and law), output reproducibility has become a strict system requirement. While practitioners use greedy decoding to eliminate algorithmic stochasticity, empirical deployments with 16-bit precisions still exhibit catastrophic output divergence across heterogeneous GPUs. Through SASS-level profiling, we reveal that this inconsistency is fundamentally driven by truncation errors introduced during downcasting at kernel boundaries. However, achieving reproducibility via a global FP32 pipeline incurs prohibitive system penalties: bypassing 16-bit hardware accelerators hurts compute efficiency, while upcasting the KV cache doubles memory overhead. To bridge this gap, we propose Hybrid Error ALleviation (HEAL), a targeted intervention that approximates FP32 precision while resolving hardware constraints through two targeted mechanisms. First, recognizing that floating-point formats underutilize their bit-width for Q, K, V tensors, HEAL applies INT16 quantization that preserves numerical stability without expanding the KV cache footprint. Second, HEAL synthesizes high-precision matrix multiplications via an algebraic error compensation strategy, executing entirely on high-throughput 16-bit Tensor Cores. To evaluate our approach practically, we introduce MCR-Bench, a benchmark targeting reproducibility in mission-critical tasks. HEAL achieves the same level of reproducibility on downstream tasks as the FP32 baseline while reducing the performance overhead by up to 7.1x.

Zhenting Zhu, Lucas Thai, Shan Yu +5

1UCLA · 2UC Berkeley · University of Chinese Academy of Sciences

Mixed-Precision Quantization LLM Inference

Jun 18, 2026cs.IR

The Token Tax of Epistemic Accuracy: Comparing RAG and Long-Context Architectures for Document-Grounded Generative AI Applications

Document-grounded assistants built on large language models are increasingly used in high-stakes, knowledge-intensive work. Their usefulness, however, may depend on how evidence is allocated before generation. We investigate such a claim by comparing two grounding architectures: (a) retrieval-augmented generation (RAG) that retrieves a few relevant passages, and (b) long-context prompting, which loads the whole document collection in context. We view these as two regimes of "epistemic access" on an accuracy--cost frontier. We use "epistemic accuracy" to capture model correctness that depends on having the right evidence. We posit that broader access (via long context) can increase it, but with a "token tax" (i.e., a substantial increase in cost due to larger input token consumption). We probe this framing with a case study in manufacturing safety training. Using an expert-validated benchmark, we evaluate 972 answers across three machines, two small language models, and three retrieval/in-context prompting approaches. Long-context prompting achieved the highest correctness (73.1% vs. 65.4% for semantic RAG), but at 26 times the per-query token cost. We interpret this gap as the token tax of broader evidentiary access. We carefully discuss the implications of our findings for resource-constrained organizations.

Austin Hamilton, Ryan Singh, Michael Wise +6

Miami University · University at Buffalo

LLM Grounding LLM Inference LLM Prompting Document QA RAG Evaluation

Jun 17, 2026cs.LG

Structured Inference with Large Language Gibbs

The knowledge encoded in large language models (LLMs) can serve as a substrate for structured reasoning over variables describing a complex world, but accessing this knowledge in a probabilistically coherent manner poses a difficult inference problem. We propose Large Language Gibbs, a scheme for structured probabilistic inference that uses conditional distributions of an LLM as transition operators. Rather than sampling structured objects through single-pass autoregressive generation, we iteratively resample individual variables conditioned on others using an LLM's next-token conditionals. This approach avoids order-dependent biases and produces a stationary distribution that reflects a compromise between all local conditionals. We apply this approach to sampling from synthetic distributions, consistent reasoning tasks, and Bayesian structure learning. The results suggest that the use of LLM conditionals in MCMC is a practical alternative to one-pass generation for structured probabilistic inference under a world prior accessible through noisy LLM conditionals.

Sanghyeok Choi, Henry Gouk, Esmeralda S. Whitammer

University of Edinburgh, School of Informatics · 2CIFAR Fellow, Learning in Machines and Brains

Markov Chain Monte Carlo LLM Inference Bayesian Inference Structured Reasoning

Jun 16, 2026cs.AI

How Inference Compute Shapes Frontier LLM Evaluation

AI evaluations are shifting toward harder tasks that benefit from longer trajectories involving tool use and iterative problem solving. As a result, performance is increasingly sensitive to the amount and allocation of compute available at test time ("inference compute"). Yet many evaluations still report performance at a single restrictive budget, meaning that low scores may reflect the evaluation setup rather than the model's underlying capability. To test this, we evaluate up to 12 frontier language models on seven challenging benchmarks spanning software engineering, mathematics, medicine, and cybersecurity. We use a controlled setup combining three simple inference-scaling interventions: larger token budgets, context compaction, and repeated submission attempts, guided either by the model itself or by minimal correctness feedback. We find three main results. First, larger token budgets substantially improve performance on benchmarks across multiple domains, including cybersecurity, FrontierMath, Humanity's Last Exam, and TerminalBench. Second, fixed-budget evaluations can increasingly understate frontier capability as models advance. Newer models reach higher performance at large budgets, where they unlock harder tasks and solve them more reliably. Third, benchmarks differ in which inference-scaling methods help most: repeated submission broadly improves performance, but the value of larger token budgets, external feedback, and parallel attempts varies by benchmark. Overall, our results show that benchmark scores are protocol-dependent. We therefore argue that evaluations should report capability as a function of inference-time compute, specify protocol choices explicitly, and compare model generations over a large shared compute range at matched budgets, especially in safety- or policy-relevant settings.

Jessica McFadyen, Ole Jorgensen, Harry Coppock +2

AI Security Institute, London, UK · University of Oxford, Oxford, UK · Harvard University, Cambridge, MA, USA

LLM Evaluation Language Model Generation Evaluation LLM Inference Inference-Time Scaling

Jun 15, 2026cs.LG

Entropy-Gated Latent Recursion

Inference-time scaling has become the dominant lever for improving language-model reasoning, but existing methods derive rollout diversity from a single source: stochastic token-level sampling. We argue that this single-axis sampling space is fundamentally limiting, and identify a second, fully deterministic and complementary axis: the layer span

L

at which a frozen model's top decoder layers are recursively re-applied at high-uncertainty tokens. Different choices of

L

produce distinct rollouts that solve different subsets of problems, with no stochasticity. We instantiate this axis through Entropy-Gated Latent Recursion (EGLR), a training-free decoding procedure that re-applies the top-

L

layers for at most

K_{\max}

iterations until the next-token distribution converges. Combined with

T

temperature samples, EGLR turns a single-axis stochastic rollout pool into an

L\times T

Cartesian sampling space at almost the same per-rollout cost. We characterize this space across

8

instruction-tuned models and

6

math reasoning benchmarks, and show that the

L

-axis is genuinely complementary to temperature: on MATH-500 with Qwen2.5-3B-Instruct, the joint

L\times T

oracle reaches

91.6\%

,

+8.2

percentage points beyond the temperature-only oracle (

83.4\%

) and

+10.4

points beyond the layer-only oracle (

81.2\%

), confirming that the two axes capture genuinely complementary problems. The expanded rollout pool provides richer per-prompt candidates for any downstream procedure that consumes rollouts, including self-consistency, best-of-

N

with verifiers, and group-relative RL training (GRPO), opening a new direction for inference-time scaling that does not rely on stochastic noise.

Soham Bhattacharjee, Dushyant Singh Chauhan, Salem Lahlou +2

Department of Machine Learning Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi, United Arab Emirates

LLM Inference Inference-Time Scaling Efficient Language Model Reasoning LLM Reasoning Recursive Language Models

Jun 15, 2026cs.LG

Privacy from Symmetry: Orthogonally Equivariant Transformers for LLM Inference

Running large language models locally is often impractical, pushing inference on sensitive text to third-party providers. Split inference partially mitigates this by keeping tokens on the client and sending only hidden representations, but these representations can still be recovered via nearest-neighbor search against the public embedding table. We propose an orthogonal obfuscation procedure in which the client multiplies embeddings by a secret orthogonal matrix before transmission. To enable correct inference under arbitrary rotations, we introduce ConjFormer, a transformer variant that is exactly

\mathrm{O}(d)

-equivariant via a lightweight normalization change (scalar RMSNorm) together with blockwise orthogonal conjugation of all linear weights. As a result, the server performs the full forward pass entirely in the rotated basis and never observes unrotated hidden states. Experiments on GPT-2 and Llama 3.2 1B models fine-tuned on PubMed show that orthogonal obfuscation eliminates direct cosine nearest-neighbor inversion and reduces token recovery from over 35% top-10 to at most 1.3%, while increasing perplexity by only 0.4% after fine-tuning. These results indicate that enforcing symmetry at the architectural level can provide a practical defense for privacy-preserving LLM inference without noise injection or heavy cryptographic machinery.

Alexander Yukhimchuk, Andrey Shulga, Mladen Kolar +1

MBZUAI · University of Southern California

Privacy-Preserving Language Models LLM Inference Equivariant Neural Networks Split Inference Privacy Leakage in Language Models

Jun 15, 2026cs.LG

Communication-Efficient Verifiable Attention for LLM Inference

Computation integrity of remote large language model (LLM) serving can be questionable. For conventional deep neural networks (DNNs), the existing TEE-shielded DNN partitioning (TSDP) approach uses Trusted Execution Environment (TEE) to compute non-linear components and verify the integrity of linear components offloaded to an untrusted GPU. However, directly applying TSDP to Transformer-based LLMs incurs significant TEE computation and TEE-GPU communication overhead. This paper presents Communication-efficient TEE-GPU Attention (\textsc{VeriAttn}) for accelerating verifiable LLM inference. \textsc{VeriAttn} offloads both linear and non-linear computations of attention to the GPU, while TEE performs verification. Moreover, for prefill, \textsc{VeriAttn} uses a two-level pipeline to overlap data movement, TEE pre-/post-processing, and GPU computation. For decoding, when the key-value cache exceeds available GPU memory, \textsc{VeriAttn} partitions attention across TEE and GPU to reduce repeated key-value transfers. Evaluation on an Intel TDX platform shows that \textsc{VeriAttn} achieves 2.60-3.38

\times

and 3.86-5.42

\times

acceleration over TSDP for 6k-token prompts and 10k-token outputs during prefill and decoding, respectively.

Ziqun Chen, Ming Wu, Michael Heinrich +4

Nanyang Technological University · Singapore · Zero Gravity Labs +1

LLM Inference Trusted Execution Environments Transformer Attention LLM Inference Acceleration