LLM Serving

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

17 papers in the last four weeks, up 143% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 144

May 22, 2026cs.AI

Identifying and Mitigating Systemic Measurement Bias in Production LLM Inference Benchmarks

As Large Language Models (LLMs) transition from research environments to production deployments, evaluating their performance against strict Service Level Objectives (SLOs) has become critical. However, current evaluation methodologies suffer from severe measurement bias at scale. We demonstrate that widely used benchmarking utilities rely on single-process, asyncio-driven architectures that introduce fundamental client-side queuing bottlenecks under high concurrency. By modeling the benchmarking client as an

M/G/1

queue, we mathematically demonstrate how the Python Global Interpreter Lock (GIL) artificially inflates Time to First Token (TTFT) and Time Per Output Token (TPOT) metrics as request rates scale. To resolve this systematic inaccuracy, we propose an unbiased, multi-process evaluation framework that effectively distributes client-side load, ensuring negligible queuing overhead. Furthermore, we formalize a composite metric, Normalized Time Per Output Token (NTPOT), to robustly amortize end-to-end latency, including prefill and scheduling delays across sequence lengths. Our empirical evaluation demonstrates that this methodology successfully isolates pure serving engine performance, enabling accurate, reproducible profiling of LLMs at production scales exceeding thousands of queries per second.

Ashok Chandrasekar, Jason Kramberger

Google

LLM Evaluation LLM Serving LLM Inference Benchmark Design

May 21, 2026cs.LG

ModeSwitch-LLM: A Lightweight Phase-Aware Controller for Cross-Mode LLM Inference on a Single GPU

ModeSwitch-LLM is a lightweight request-boundary controller for improving single-GPU large language model inference efficiency by routing each request to an appropriate fixed inference mode. Instead of relying on one static serving configuration, the system selects among FP16, quantized modes, speculative decoding, and hybrid modes such as GPTQ plus prefix caching and INT8 plus continuous batching using cheap workload-level features. We evaluate ModeSwitch-LLM on Meta-Llama-3.1-8B-Instruct served on a single NVIDIA A100 GPU. On deployment-style synthetic workloads, the online controller achieves a 2.10x mean latency speedup over FP16 and a 0.48x mean energy ratio, corresponding to 51.7% lower energy per token. On automatic benchmarks used as a quality gate, accuracy remains close to FP16 with a mean delta of +0.17 percentage points. We also evaluate lightweight learned routers, but find that they do not clearly outperform the rule-based controller because they add routing overhead and more often select modes that violate quality, energy, or memory constraints. These results show that simple request-aware routing can recover substantial efficiency from existing inference modes without retraining the model or changing its architecture.

Aman Sunesh, Ali Alshehhi, Hivansh Dhakne

Department of Computer Engineering NYU Abu Dhabi Abu Dhabi, United Arab Emirates · Courant Institute of Mathematical Sciences New York University New York, United States · Department of Computer Engineering New York University New York, United States

LLM Inference Efficiency LLM Serving GPU Acceleration LLM Inference LLM Inference Scheduling LLM Routing

May 20, 2026cs.MA

Argo: Efficient Importance Labeling for Enterprise Email Systems

Email importance labeling has long been a critical yet challenging problem for businesses and individuals. Traditional approaches; such as keyword matching, user-defined rules, and sender-based heuristics; demand extensive manual feature engineering and fail to scale effectively or generalize. Recent advances in large language models (LLMs) demonstrate strong potential and a natural fit for this task, offering deep contextual understanding and superior labeling quality. However, using LLM models like GPT-4.1 at enterprise email volumes incurs prohibitive computational costs and hinders real-world deployment. We explore the trade-off space of using alternative labeling schemes as opposed to GPT4.1 scale LLMs, with the goal of achieving near GPT level labeling quality with significantly lower cost. We develop Argo, an enterprise email labeling framework, where we construct a profiler to efficiently search the cost quality trade-off space of labeling and identify cost-efficient alternatives to labeling emails. Additionally, we design an on-demand provisioning scheme to intelligently scale Argo with real time load, to minimize cost increases during peak load inference. Over 3 open-source email datasets, Argo achieves 148-167X inference cost reduction with negligible quality degradation and 20-640000X lower profiling costs, making large-scale, context-aware email labeling practical for enterprises.

Siddhant Ray, Ganesh Ananthanarayanan, Kevin Chian +5

University of Chicago · Microsoft · University of Chicago / TensorMesh

LLM Inference Efficiency LLM Serving Cost-Aware Inference Text Classification

May 20, 2026cs.AI

PALS: Power-Aware LLM Serving for Mixture-of-Experts Models

Large language model (LLM) inference has become a dominant workload in modern data centers, driving significant GPU utilization and energy consumption. While prior systems optimize throughput and latency by batching, scheduling, and parallelism, they largely treat GPU power as a static constraint rather than a controllable resource. In this paper, we present a power-aware runtime for LLM serving, PALS, that treats GPU power caps as a first-class control knob and jointly optimizes them with software parameters such as batch size. The system combines lightweight offline power-performance models with a feedback-driven controller to select configurations that satisfy throughput targets while maximizing energy efficiency. We implement PALS within an existing LLM serving framework, vLLM, demonstrating that it requires no model retraining or API changes. Across multi-GPU systems and both dense and mixture-of-experts (MoE) models, PALS improves energy efficiency by up to 26.3%, reduces QoS violations by 4x to 7x under power constraints, and tracks dynamic power budgets. These results highlight the potential of integrating power control directly into LLM inference runtimes, enabling energy-proportional and grid-interactive AI systems.

Can Hankendi, Rana Shahout, Minlan Yu +1

Boston University · Electrical and Computer Engineering Department · Boston, MA, USA +3

LLM Inference Efficiency LLM Serving Energy-Efficient ML

May 20, 2026cs.DC

Frontier: Towards Comprehensive and Accurate LLM Inference Simulation

Modern LLM serving is no longer homogeneous or monolithic. Production systems now combine disaggregated execution, complex parallelism, runtime optimizations, and stateful workloads such as reasoning, agents, and RL rollouts. Simulation is attractive for exploring this growing design space, yet existing simulators lack the architectural completeness and decision-grade fidelity it demands. Their monolithic-replica abstractions are ill-suited to disaggregated serving, while average-case analytical proxies can distort SLA predictions and even reverse optimization conclusions. We present Frontier, a discrete-event simulator for modern LLM inference serving. Frontier features a disaggregated abstraction. It captures the structure and dynamics of modern serving systems by modeling co-location, Prefill-Decode Disaggregation (PDD), and Attention-FFN Disaggregation (AFD) with role-specific cluster workers, incorporating key runtime optimizations (e.g., CUDA Graphs, speculative decoding) within the scheduler-batch-engine loop, and supporting stateful requests for emerging workloads. It further provides accurate and generalizable predictions of computation, communication, and memory costs across diverse serving scenarios with complex workload compositions. On 16-H800 GPU testbed, Frontier achieves an average throughput error below 4%. Compared with state-of-the-art simulators, it reduces end-to-end latency error from 44.9% to 6.4% under co-location and from 51.7% to 2.6% under disaggregation. It scales to over 1K GPUs on commodity CPUs and enables new use cases such as SLA-dependent Pareto frontier exploration, heterogeneous disaggregated allocation, agentic reasoning scheduling validation, and RL post-training reconfiguration. We release Frontier at https://github.com/NetX-lab/Frontier.

Yicheng Feng, Xin Tan, Yangtao Deng +3

The Chinese University of Hong Kong · Anuttacon · StepFun

LLM Serving Disaggregated LLM Serving LLM Inference Scheduling LLM Inference Serving Distributed Inference

May 20, 2026cs.DC

PlexRL: Cluster-Level Orchestration of Serviceized LLM Execution for RLVR

Reinforcement learning with verifiable rewards (RLVR) has recently unlocked strong reasoning capabilities in large language models (LLMs), triggering rapid exploration of new algorithms and data. However, RLVR training is notoriously inefficient: long-tailed rollouts, tool-induced stalls, and asymmetric resource requirements between rollout and training introduce substantial idle time that cannot be eliminated by job-local optimizations such as synchronous pipelining, asynchronous rollout, or colocated execution. We argue that this inefficiency is structural. While idle gaps are unavoidable within individual RLVR jobs, they are largely anti-correlated across jobs and therefore exploitable at the cluster level. Leveraging this observation, we present PlexRL, a cluster-level runtime for multiplexing unified LLM services across RLVR jobs. By centrally managing model placement, state transitions, and function-level scheduling under strict affinity constraints, PlexRL time-slices LLM execution across jobs to fill otherwise idle periods without expensive model migration. Our implementation and evaluations demonstrate that PlexRL significantly improves effective cluster capacity and reduces user GPU hour cost by maximum 37.58% while preserving algorithmic flexibility and introducing minimal per-job overhead.

Yiqi Zhang, Fangzheng Jiao, Tian Tang +13

National University of Singapore · Shanghai Qiji Zhifeng Co., Ltd. · Beihang University +3

LLM Inference Efficiency LLM Serving Reinforcement Learning with Verifiable Rewards

May 19, 2026cs.AI

Towards Multi-Model LLM Schedulers: Empirical Insights into Offloading and Preemption

Modern deployments of Large Language Models (LLMs) increasingly require serving multiple models with diverse architectures, sizes, and specialization on shared, heterogeneous hardware. This setting introduces new challenges for resource allocation, dispatching, and scheduling, particularly under GPU memory constraints where partial CPU-GPU offloading and preemption become necessary. While existing systems primarily optimize throughput for a single model, comparatively little work addresses multi-model scheduling under these conditions. In this paper, we present an empirical study of how different LLMs behave across hardware platforms, focusing on the performance implications of layer offloading and preemption. We show that offloading leads to strongly non-linear and model-dependent degradation in decode throughput, with smaller models exhibiting sharper sensitivity to reduced GPU residency. We further demonstrate that preemption incurs substantial overhead, largely dominated by model state reload rather than key-value cache transfer, and that this cost varies significantly across models and hardware platforms. Additionally, we highlight the role of sequence length and interconnect bandwidth in amplifying data movement and execution inefficiencies. Based on these findings, we identify a set of key features that future schedulers must consider, including model-specific offloading sensitivity, workload characteristics, and the cost structure of preemption and data transfer. These insights provide guidance for the design of next-generation LLM serving systems capable of efficiently managing heterogeneous, multi-model workloads with hybrid CPU-GPU execution.

Mert Yildiz, Pietro Spadaccino, Alexey Rolich +2

Sapienza University of Rome, Rome, Italy

LLM Inference Efficiency LLM Serving LLM Inference

May 14, 2026cs.LG

An Interpretable Latency Model for Speculative Decoding in LLM Serving

Speculative decoding (SD) accelerates large language model (LLM) inference by using a smaller draft model to propose multiple tokens that are verified by a larger target model in parallel. While prior work demonstrates substantial speedups in isolated or fixed-batch settings, the behavior of SD in production serving systems remains poorly understood: request load varies over time, and effective batch size emerges from the serving system rather than being directly controlled or observed. In this work, we develop a simple and interpretable latency model for SD in LLM serving. We infer effective batch size from request rate using Little's Law and decompose per-request demand into load-independent and load-dependent components for prefill, drafting, and verification. We validate our model using extensive measurements from vLLM across verifier and drafter model sizes, prefill and decode lengths, request rates, draft lengths, and acceptance probabilities. The model accurately describes observed latency, explains why speedups often diminish as server load increases, and characterizes how draft length, acceptance rate, and verifier-drafter size shape latency across serving conditions, with implications for configuring SD in deployed systems. We further show how the framework extends to mixture of experts models, where sparse expert activation changes the effective service costs across load regimes. Together, our results provide a structured framework for understanding SD in real LLM serving systems.

Linghao Kong, Megan Flynn, Michael Peng +3

MIT · Red Hat AI

LLM Serving Speculative Decoding

May 14, 2026cs.LG

PreFT: Prefill-only finetuning for efficient inference

Large language models can now be personalised efficiently at scale using parameter efficient finetuning methods (PEFTs), but serving user-specific PEFTs harms throughput, even with specialised kernels and memory management techniques. This is because, theoretically and empirically, a mismatch exists between prefill (processing a large number of tokens at once) and decode (generating a single token autoregressively): the latter has far lower throughput when serving multiple adapters. Rather than optimising performance relative to parameter count, for efficient multi-adapter serving, we instead ought to optimise performance relative to serving throughput. We therefore propose PreFT (Prefill-only Finetuning), wherein we only apply the adapter to prefill tokens and discard it afterwards. PreFT significantly increases throughput with minimal effect on performance. We develop and release an efficient implementation of two prefill-only PEFTs, LoRA and ReFT, on the vLLM inference engine. We first show that serving multi-user PreFTs is more efficient than traditional PEFTs (

1.9\times

the throughput when serving

512

adapters on Llama 3.1 70B). Then, we compare the performance of prefill-only vs. all-token adapters on a variety of supervised finetuning and reinforcement learning tasks with LMs at varying scales. On SFT, we observe that the evaluation loss of PreFTs is higher than PEFTs, but can be compensated by increasing rank with nearly no reduction in throughput. On RL, we consistently find that PreFTs approach parity with standard PEFTs. Together, this work validates prefill-only adaptation of LLMs as a more favourable accuracy-throughput tradeoff than existing PEFTs for personalised serving.

Andrew Lanpouthakoun, Aryaman Arora, Zhengxuan Wu +4

Stanford University · Tilde Research

Fine-Tuning LLM Serving Adapter Tuning LLM Inference Acceleration Parameter-Efficient Fine-Tuning

May 13, 2026cs.LG

MinT: Managed Infrastructure for Training and Serving Millions of LLMs

We present MindLab Toolkit (MinT), a managed infrastructure system for Low-Rank Adaptation (LoRA) post-training and online serving. MinT targets a setting where many trained policies are produced over a small number of expensive base-model deployments. Instead of materializing each policy as a merged full checkpoint, MinT keeps the base model resident and moves exported LoRA adapter revisions through rollout, update, export, evaluation, serving, and rollback, hiding distributed training, serving, scheduling, and data movement behind a service interface. MinT scales this path along three axes. Scale Up extends LoRA RL to frontier-scale dense and MoE architectures, including MLA and DSA attention paths, with training and serving validated beyond 1T total parameters. Scale Down moves only the exported LoRA adapter, which can be under 1% of base-model size in rank-1 settings; adapter-only handoff reduces the measured step by 18.3x on a 4B dense model and 2.85x on a 30B MoE, while concurrent multi-policy GRPO shortens wall time by 1.77x and 1.45x without raising peak memory. Scale Out separates durable policy addressability from CPU/GPU working sets: a tensor-parallel deployment supports 10^6-scale addressable catalogs (measured single-engine sweeps through 100K) and thousand-adapter active waves at cluster scale, with cold loading treated as scheduled service work and packed MoE LoRA tensors improving live engine loading by 8.5-8.7x. MinT thus manages million-scale LoRA policy catalogs while training and serving selected adapter revisions over shared 1T-class base models.

Mind Lab, :, Song Cao +60

LLM Serving Adapter Tuning Low-Rank Adaptation LLM Inference Acceleration

May 13, 2026cs.DC

KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving

LLMs are widely adopted in production, pushing inference systems to their limits. Disaggregated LLM serving (e.g., PD separation and KV state disaggregation) improves scalability and cost efficiency, but it also turns KV into an explicit payload crossing network and storage boundaries, making KV a dominant end-to-end bottleneck. Existing KV compression are typically static runtime configurations, despite production service context varies over time in workload mix, bandwidth, and SLO/quality budgets. As a result, a fixed choice can be suboptimal or even increase latency. We present \emph{KVServe}, the first service-aware and adaptive KV communication compression framework for disaggregated LLM serving: KVServe (1) unifies KV compression into a modular strategy space with new components and cross-method recomposition; (2) introduces Bayesian Profiling Engine that efficiently searches this space and distills a 3D Pareto candidate set, reducing

50\times

offline search overhead; and (3) deploys a Service-Aware Online Controller that combines an analytical latency model with a lightweight bandit to select profiles under constraints and correct offline-to-online mismatch. Integrated into vLLM and evaluated across datasets, models, GPUs and networks, KVServe achieves up to

9.13\times

JCT speedup in PD-separated serving and up to

32.8\times

TTFT reduction in KV-disaggregated serving.

Zedong Liu, Xinyang Ma, Dejun Luo +9

University of Chinese Academy of Sciences · Institute of Computing Technology, Chinese Academy of Sciences · Shanghai Jiao Tong University

LLM Serving KV Caching Disaggregated LLM Serving KV-Cache Compression

May 13, 2026cs.DC

MARLIN: Multi-Agent Game-Theoretic Reinforcement Learning for Sustainable LLM Inference in Cloud Datacenters

Large Language Models (LLMs) have become increasingly prevalent in cloud-based platforms, propelled by the introduction of AI-based consumer and enterprise services. LLM inference requests in particular account for up to 90% of total LLM lifecycle energy use, dwarfing training energy costs. The rising volume of LLM inference requests is increasing environmental footprints, particularly carbon emissions and water consumption. To improve sustainability for LLM inference serving in cloud datacenter environments, we propose a novel multi-agent game-theoretic reinforcement learning framework called MARLIN to co-optimize time-to-first token (TTFT), carbon emissions, water usage, and energy costs associated with LLM inference. MARLIN demonstrates a reduction of at least 18% in TTFT, 33% in carbon emissions, 43% in water usage, and 11% in energy costs compared to state-of-the-art LLM inference management frameworks.

H. Moore, S. Qi, D. Milojicic +2

Colorado State University Fort Collins, CO, USA · Hewlett Packard Labs Milpitas, CA, USA

LLM Serving LLM Inference Game Theory Multi-Agent Reinforcement Learning

May 11, 2026cs.CL

SOMA: Efficient Multi-turn LLM Serving via Small Language Model

Large Language Models (LLMs) are increasingly deployed in multi-turn dialogue settings where preserving conversational context across turns is essential. A standard serving practice concatenates the full dialogue history at every turn, which reliably maintains coherence but incurs substantial cost in latency, memory, and API expenditure, especially when queries are routed to large proprietary models. Existing approaches often struggle to balance the trade-off between response quality and efficiency. We propose a framework that exploits the early turns of a session to estimate a local response manifold and then adapt a smaller surrogate model to this local region for the remainder of the conversation. Concretely, we learn soft prompts that maximize semantic divergence between the large and surrogate small language models' responses to surface least-aligned local directions, stabilize training with anti-degeneration control, and distill the mined cases into localized LoRA fine-tuning so the surrogate runs without prompts at inference. A simple gate enables a one-time switch with rollback on drift. We further provide a theoretical analysis for key components in SOMA. Extensive experiments show the effectiveness of SOMA. The source code is provided at: https://github.com/LabRAI/SOMA.

Xueqi Cheng, Qiong Wu, Zhengyi Zhou +3

Florida State University · AT&T Chief Data Office · Louisiana State University +1

LLM Serving Small Language Models Language Model Distillation Efficient Language Model Inference

May 11, 2026cs.AI

Rethinking LLMOps for Fraud and AML: Building a Compliance-Grade LLM Serving Stack

Fraud detection and anti-money-laundering (AML) compliance are high-value domains for large language models (LLMs), but their serving requirements differ sharply from generic chat workloads. Compliance prompts are often prefix-heavy, schema-constrained, and evidence-rich, combining reusable policy instructions, risk taxonomies, transaction or document context, and short structured outputs such as JSON labels or risk factors. These properties make prefix reuse, KV-cache efficiency, runtime tuning, model orchestration, and output validation first-order systems concerns. This paper introduces a workload-aware LLMOps stack for fraud and AML workloads using self-hosted open-weight models such as Meta Llama and Alibaba Qwen. The stack combines vLLM-style runtime tuning, PagedAttention, Automatic Prefix Caching, multi-adapter serving, adapter and prompt-length-aware batching, sleep/wake lifecycle management, speculative decoding, and optional prefill/decode disaggregation. To avoid exposing institution-specific data, the reproducibility track converts public synthetic AML datasets, including IBM AML and SAML-D, into prefix-heavy compliance prompts with reusable policy text, transaction evidence, typology definitions, and schema-constrained outputs. We also incorporate an LLM-as-judge quality gate using deterministic compliance checks, reference metrics, expert-adjudicated calibration data where available, and multi-judge rubric scoring. Across public-synthetic AML workloads and controlled serving benchmarks, workload-aware tuning improved throughput from 612-650 to 3,600 requests/hour, reduced P99 latency from 31-38 seconds to 6.4-8.7 seconds, and increased GPU utilization from 12% to 78%. These results show that regulated LLM performance is a workload-design, serving-optimization, and quality-gating problem, not only a model-selection problem.

Prathamesh Vasudeo Naik, Naresh Dintakurthi, Yue Wang

LLM Serving Financial Fraud Detection LLM Inference Acceleration

May 11, 2026cs.CR

Continuous Discovery of Vulnerabilities in LLM Serving Systems with Fuzzing

LLM inference and serving systems have become security-critical infrastructure; however, many of their most concerning failures arise from the serving layer rather than from model behavior alone. Modern inference engines combine KV cache, batching, prefix sharing, speculative decoding, adapters, and multi-tenant scheduling, creating shared-state behavior that only emerges under realistic concurrent workloads and is missed by standard model, safety, and API tests. We present GRIEF, a greybox fuzzer for LLM inference engines that treats timed multi-request traces as first-class inputs, uses lightweight oracles to detect crashes, hangs, performance pathologies, and silent output corruption, and applies controlled replay with log-probability checks to confirm reproducible serving-layer failures. Across early campaigns on vLLM and SGLang, GRIEF discovers 15 vulnerabilities, 10 confirmed by engine developers, including 2 CVEs, spanning KV-cache isolation failures, cross-request performance interference, and crash or liveness bugs. These results show that concurrency, caching, and state reuse can induce silent cross-request contamination, noisy-neighbor denial of service, and delayed crashes without malformed inputs or explicit server errors, making concurrent serving behavior a first-class security and reliability boundary for LLM infrastructure.

Yunze Zhao, Yibo Zhao, Yuchen Zhang +2

University of Maryland · New York University

LLM Serving LLM Security

May 10, 2026cs.DC

PEEK: Predictive Queue-Informed KV Cache Management for LLM Serving

We present PEEK, a lightweight scheduling and eviction framework for both online (streaming) and offline (batch) LLM serving; this paper focuses on the online regime. PEEK maintains an incremental radix tree over the pending queue, exposing prefix-sharing clusters no existing engine surfaces. A low-overhead dual-walk matches the tree against the engine's prefix cache to yield longest-prefix-match for every waiting request; PEEK then admits cluster pioneers first so siblings inherit the freshly cached prefix, a co-designed eviction hook protects blocks ancestral to queued demand, and a multi-lane stride scheduler bounds starvation. On SGLang and vLLM across five workloads up to 4

\times

H100 (DP=2 over TP=2), PEEK delivers up to 3.0

\times

/2.6

\times

cache hit, 7.9

\times

/7.1

\times

TTFT, 6.7

\times

/5.5

\times

E2E, and 3.6

\times

/4.5

\times

throughput gains over each engine's strongest stock baseline (SGLang/vLLM), while matching baselines within noise on workloads with no exploitable prefix structure. Wins hold as KV-cache pressure and inference parallelism scale.

Bing Xie, Zhipeng Wang, Masahiro Tanaka +1

†Corresponding author.

LLM Serving KV Caching KV-Cache Eviction KV-Cache Management Prefix Caching KV-Cache Reuse

May 9, 2026cs.LG

PRISM: Fast Online LLM Serving via Scheduling-Memory Co-design

Modern online large language model (LLM) services, such as Retrieval-Augmented Generation (RAG) and agent systems, increasingly expose two prominent characteristics: prompt segmentation (e.g., system instructions, retrieved passages, tool outputs) and hotspot skew, where a small set of these segments recurs frequently across user requests. Failing to jointly exploit these patterns could lead to repeated prefill of hot segments and prolonged TTFT, undermining both throughput and user-perceived responsiveness. However, existing work tackles these patterns independently: KV-cache management mainly exploits segment reuse while scheduling reorders requests to improve cache locality, yet neither aligns request admission with KV-cache retention. To address this gap, we first analyze how scheduling and KV-cache management jointly affect TTFT. Guided by this, we present PRISM (Prefix Reuse Optimization Integrated Scheduling and Memory), which co-designs a query-aware scheduler (QAS) with a demand-aware radix tree (DART) to align request admission with exact-prefix KV retention. Our evaluation results show that, versus the strongest baseline, PRISM reduces average per-QPS P99 TTFT by 23.3% and 37.1% while increasing exact-prefix KV-cache hit rate by 5.9 and 12.2 percentage points on 4B and 13B models, respectively.

Xingyu Qu, Tianhao Lin, Yiqi Li +2

School of Computer Science, Wuhan University · Amazon

LLM Serving KV Caching KV-Cache Management LLM Inference Acceleration Prefix Caching LLM Request Scheduling

May 7, 2026cs.DC

Regulating Branch Parallelism in LLM Serving

Recent methods expose intra-request parallelism in LLM outputs, allowing independent branches to decode concurrently. Existing serving systems execute these branches eagerly or under fixed caps. We show that both are brittle: eager admission inflates the shared decode step, degrading co-batched requests in serial stages, while conservative fixed caps forgo the throughput that motivated exposing branches in the first place. We call the excess step latency caused by admitted branches the branch externality and show that the safe width depends on batch composition, context lengths, and accumulated slack, all of which change continuously over a workload trace. We introduce TAPER, a per-step admission controller that treats extra branches as opportunistic work, admitted only when the predicted branch externality fits within the batch's current slack budget. Per-step regulation is practical because branch-level scheduling decouples compute from memory: branches share the request's prefix KV, so expanding or contracting width requires no memory reclamation. On Qwen3-32B, TAPER improves goodput by

1.77\times

over IRP-Off and by

1.48\times

over IRP-Eager, while maintaining over

95\%

SLO attainment.

Swapnil Gandhi, Siva Hari, William J. Dally +1

1Stanford University · 2NVIDIA

LLM Serving LLM Inference Scheduling LLM Inference Serving Parallel Decoding

May 7, 2026cs.AI

VibeServe: Can AI Agents Build Bespoke LLM Serving Systems?

For years, we have built LLM serving systems like any other critical infrastructure: a single general-purpose stack, hand-tuned over many engineer-years, meant to support every model and workload. In this paper, we take the opposite bet: a multi-agent loop that automatically synthesizes bespoke serving systems for different usage scenarios. We propose VibeServe, the first agentic loop that generates entire LLM serving stacks end-to-end. VibeServe uses an outer loop to plan and track the search over system designs, and an inner loop to implement candidates, check correctness, and measure performance on the target benchmark. In the standard deployment setting, where existing stacks are highly optimized, VibeServe remains competitive with vLLM, showing that generation-time specialization need not come at the cost of performance. More interestingly, in non-standard scenarios, VibeServe outperforms existing systems by exploiting opportunities that generic systems miss in six scenarios involving non-standard model architectures, workload knowledge, and hardware-specific optimizations. Together, these results suggest a different point in the design space for infrastructure software: generation-time specialization rather than runtime generality. Code is available at https://github.com/uw-syfi/vibe-serve.

Keisuke Kamahori, Shihang Li, Simon Peter +1

University of Washington

Multi-Agent LLM Systems LLM Serving AI Coding Agents

May 6, 2026cs.LG

A Queueing-Theoretic Framework for Stability Analysis of LLM Inference with KV Cache Memory Constraints

The rapid adoption of large language models (LLMs) has created significant challenges for efficient inference at scale. Unlike traditional workloads, LLM inference is constrained by both computation and the memory overhead of key-value (KV) caching, which accelerates decoding but quickly exhausts GPU memory. In this paper, we introduce the first queueing-theoretic framework that explicitly incorporates both computation and GPU memory constraints into the analysis of LLM inference. Based on this framework, we derive rigorous stability and instability conditions that determine whether an LLM inference service can sustain incoming demand without unbounded queue growth. This result offers a powerful tool for system deployment, potentially addressing the core challenge of GPU provisioning. By combining an estimated request arrival rate with our derived stable service rate, operators can calculate the necessary cluster size to avoid both costly over-purchasing and performance-violating under-provisioning. We further validate our theoretical predictions through extensive experiments in real GPU production environments. Our results show that the predicted stability conditions are highly accurate, with deviations typically within 10%.

Chengyi Nie, Nian Si, Zijie Zhou

Department of Electrical and Computer Engineering, Stony Brook University · Department of Industrial Engineering and Decision Analytics, HKUST

LLM Serving LLM Inference LLM Inference Scheduling LLM Inference Serving Memory-Efficient Inference

May 5, 2026cs.DC

Coral: Cost-Efficient Multi-LLM Serving over Heterogeneous Cloud GPUs

The usage of large language models (LLMs) has grown increasingly fragmented, with no single model dominating. Meanwhile, cloud providers offer a wide range of mid-tier and older-generation GPUs that enjoy better availability and deliver comparable performance per dollar to top-tier hardware. To efficiently harness these heterogeneous resources for serving multiple LLMs concurrently, we introduce Coral, an adaptive heterogeneity-aware multi-LLM serving system. The key idea behind Coral is to jointly optimize resource allocation and the serving strategy of each model replica across all models. To keep pace with shifting throughput demand and resource availability, Coral applies a lossless two-stage decomposition that preserves joint optimality while cutting online solve time from hours to tens of seconds. Our evaluation across 6 models and 20 GPU configurations shows that Coral reduces serving cost by up to 2.79

\times

over the best baseline, and delivers up to 2.39

\times

higher goodput under scarce resource availability.

Yixuan Mei, Zikun Li, Zixuan Chen +5

Carnegie Mellon University · Peking University

LLM Serving Cost-Aware Inference Cloud Computing Heterogeneous Computing Online Resource Allocation

May 5, 2026cs.CL

When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning

In single-stream autoregressive interfaces, the same tokens both update the model state and constitute an irreversible public commitment. This coupling creates a silence tax: additional deliberation postpones the first task-relevant content, while naive early streaming risks premature commitments that bias subsequent generations. We introduce Side-by-Side (SxS) Interleaved Reasoning, which makes disclosure timing a controllable decision within standard autoregressive generation. SxS interleaves partial disclosures with continued private reasoning in the same context, but releases content only when it is supported by the reasoning so far. To learn such pacing without incentivizing filler, we construct entailment-aligned interleaved trajectories by matching answer prefixes to supporting reasoning prefixes, then train with SFT to acquire the dual-action semantics and RL to recover reasoning performance under the new format. Across two Qwen3 architectures/scales (MoE Qwen3-30B-A3B, dense Qwen3-4B) and both in-domain (AIME25) and out-of-domain (GPQA-Diamond) benchmarks, SxS improves accuracy--content-latency Pareto trade-offs under token-level proxies such as inter-update waiting.

Jiaqi Wei, Xuehang Guo, Pengfei Yu +5

Zhejiang University · College of William and Mary · University of Illinois Urbana-Champaign +4

LLM Serving LLM Reasoning

May 4, 2026cs.DC

SPECTRE: Hybrid Ordinary-Parallel Speculative Serving for Resource-Efficient LLM Inference

LLM serving platforms are increasingly deployed as multi-model cloud systems, where user demand is often long-tailed: a few popular large models receive most requests, while many smaller tail models remain underutilized. We propose \textbf{SPECTRE} (Parallel \textbf{SPEC}ulative Decoding with a Multi-\textbf{T}enant \textbf{RE}mote Drafter), a serving framework that reuses underutilized tail-model services as remote drafters for heavily loaded large-model services through speculative decoding. SPECTRE enables draft generation and target-side verification to run in parallel, and makes such parallelism effective through three techniques: a hybrid ordinary-parallel speculative decoding strategy guided by a threshold derived from throughput analysis, speculative priority scheduling to preserve draft--target overlap under multi-tenant traffic, and draft-side prompt compression to reduce draft latency. We implement SPECTRE in \texttt{SGLang} and evaluate it across multiple draft--target model pairs, reasoning benchmarks, real-world long-context workloads, and a wide range of batch sizes. Results show that SPECTRE consistently improves large-model serving throughput while causing only minor interference to the native workloads of tail-model services. In large-model deployments, including Qwen3-235B-A22B with TP=8, SPECTRE achieves up to \textbf{2.28

\times

speedup} over autoregressive decoding and up to an additional \textbf{66% relative improvement} over the strongest speculative decoding baselines. Talk is cheap, we show you the code: https://github.com/sgl-project/sglang/pull/22272.

Jincheng Xie, Yawen Ling, Qi Xiao +4

1Tsinghua University · 2AI Infra Team at JDT · 3JD iCity, JD Technology, JD Intelligent Cities Research

LLM Serving Speculative Decoding

May 3, 2026cs.CL

Benchmarking KV-Cache Optimizations across Task Quality and System Performance for Long-Context Serving

Large language model serving is increasingly limited by KV-cache growth under long-context workloads, yet existing KV-cache compression techniques are difficult to compare because they were evaluated on different models, tasks, budgets, and serving stacks. This paper presents a workload-aware benchmark of representative KV-cache optimization mechanisms spanning quantization, pruning, and merging, including KIVI, TurboQuant, SnapKV, and CaM, evaluated on LongBench-style multi-document QA, single-document QA, few-shot learning, and summarization workloads using Llama-3.1-8B-Instruct and Mistral-7B-Instruct-v0.3. The benchmark measures task quality, mean output throughput, mean time-to-first-token, and realized compression ratio across context-length buckets. The results show that the compression ratio alone is a poor predictor of end-to-end performance. KIVI4 provides the most stable quality across models, SnapKV delivers the strongest long-context throughput, and CaM yields large gains on selected QA workloads but exhibits substantial workload sensitivity in both quality and realized compression ratio. These findings motivate workload-aware selection of KV-cache mechanisms rather than one-size-fits-all compression and provide deployment guidance for long-context serving systems.

Nikita Agrawal, Ruben Mayer

University of Bayreuth

LLM Serving KV Caching Long-Context Language Model Inference KV-Cache Management KV-Cache Compression KV-Cache Quantization+1

May 3, 2026cs.NI

Human-Less LLM Serving: Quantifying the Human Tax on Throughput

Every major LLM serving system is designed to meet TTFT and TPOT SLOs. These metrics capture latency as a human user perceives it, and the mechanisms built to satisfy them are now standard infrastructure. We observe that long-horizon AI tasks call LLMs programmatically in tight loops where no human observes TTFT or TPOT. We ask: how much throughput do serving systems sacrifice to meet TTFT and TPOT SLAs that these workloads never need? We conduct a systematic measurement study across chunk sizes, SLO settings, context lengths, and concurrency levels. We find that the human tax on throughput grows substantially with context length and lands in the 60-93% range. At 64K token contexts, tightening the TTFT SLO to production-typical settings costs a large fraction of throughput versus the human-less baseline. The human tax is larger at higher concurrency and is qualitatively similar across SGLang and Sarathi-Serve. We term the unconstrained optimum human-less serving and provide a prototype demonstrating that it is practical on real workloads. Our findings argue that serving systems should expose workload-class-aware SLA configurations rather than silently applying the human tax uniformly to all traffic.

Jianhui Lian, Li Chen, Dan Li +1

Tsinghua SIGS · Beijing Zhongguancun Laboratory · Tsinghua University

LLM Inference Efficiency LLM Serving

May 3, 2026cs.DC

SplitZip: Ultra Fast Lossless KV Compression for Disaggregated LLM Serving

Contemporary systems serving large language models (LLMs) have adopted prefill-decode disaggregation to load-balance between the compute-bound prefill phase and the memory-bound decode phase. Under this design, prefill workers generate a KV cache that must be transferred to decode workers before generation can begin. With these workers residing on different physical systems, this transfer becomes a significant bottleneck to serving LLMs at scale, especially for long-input and agentic workloads. Existing lossless codecs are unsuitable here as they primarily target offline weight compression, run on CPUs, or use variable-length coding whose compression cannot keep up with KV production during prefill. We introduce SplitZip, a GPU-friendly lossless compressor for KV cache transfer that preserves KV tensors bitwise and integrates into existing serving frameworks without modifying model execution. SplitZip exploits redundancy in floating-point exponents of KV activations, encoding frequent exponent values with fixed-length codes and routing rare exponents through a sparse escape stream of (position, value). A calibrated top-16 exponent codebook eliminates online histogramming, while the regular dense path and sparse escape correction make both encoding and decoding efficient on GPUs. On real BF16 activation tensors, SplitZip achieves

613.3

GB/s compression throughput and

2181.8

GB/s decompression throughput, outperforming prior lossless compressors on the critical codec path. End-to-end transfer experiments show up to

1.32\times

speedup for BF16 KV cache transfer,

1.30\times

speedup for TTFT, and

1.23\times

increase in Request Throughput. The same approach extends to FP8 KV caches, providing up to

1.14\times

compression over native E5M2. Code is available at https://github.com/Intelligent-Microsystems-Lab/SplitZip

Yipin Guo, Siddharth Joshi

University of Notre Dame IN, USA

LLM Serving KV Caching Disaggregated LLM Serving LLM Inference Acceleration KV-Cache Compression

May 3, 2026cs.LG

MoE-Prefill: Zero Redundancy Overheads in MoE Prefill Serving

Production LLM workloads increasingly serve discriminative tasks, such as classification, recommendation, and verification, whose answers are read from the logits of a single prefill pass with no autoregressive decoding. Serving these prefill-only workloads on mixture-of-experts (MoE) models is bottlenecked not by compute but by the distributed execution required to fit the model: existing parallel strategies (tensor, expert, and pipeline parallelism) trade memory pressure for redundant computation, communication, and synchronization, severely degrading MoE prefill serving efficiency. We observe that these overheads stem from coupling expert placement with synchronous activation routing -- a design inherited from the decoding era. The long, compute-bound forward passes of large-batch prefill open a per-layer window wide enough to stream expert weights in the background, replacing per-layer activation AllToAll with asynchronous weight AllGather fully overlapped with computation. We propose MoE-Prefill, a prefill-only serving system whose backend, AsyncEP (Asynchronous Expert Parallelism), gathers experts by weight rather than routing them by activation, and whose frontend co-enforces a physically-derived saturation threshold through prefix-aware routing and true-FLOPs load tracking. On Qwen3-235B-A22B across four hardware/precision configurations, MoE-Prefill delivers 1.35-1.37x throughput over the strongest distributed baseline on real-world workloads and up to 1.59x on long-context synthetic workloads, sustaining 29.8-36.2% per-GPU model FLOPs utilization.

Zhaoyuan Su, Olatunji Ruwase, Karthik Ganesan +5

University of Virginia · 2Snowflake AI Research · 3Harvard University

Expert Parallelism LLM Serving Mixture-of-Experts Inference Distributed Inference

May 2, 2026cs.DC

Position: LLM Serving Needs Mathematical Optimization and Algorithmic Foundations, Not Just Heuristics

This position paper argues that LLM inference serving has outgrown generic heuristics and now demands mathematical optimization and algorithmic foundations. Despite rapid advances in serving systems such as vLLM and SGLang, their algorithmic cores remain largely unchanged from classical distributed computing: request routing uses join-shortest-queue or round-robin, scheduling defaults to FIFO, and KV cache eviction follows LRU. These general-purpose policies ignore the distinctive structure of LLM inference--dynamically growing KV cache memory, prefill-decode phase asymmetry, unknown output lengths, and continuous batching constraints. We contend that the field must develop mathematical models capturing these characteristics, enabling the design of algorithms with provable performance guarantees across diverse workloads, rather than heuristics that may succeed in some scenarios but fail unpredictably in others. Emerging work at the intersection of operations research and ML systems demonstrates that principled methods can match or exceed heuristic performance while providing theoretical guarantees. We call on the community to recognize algorithmic design for LLM serving as a research frontier.

Zijie Zhou

Department of Industrial Engineering and Decision Analytics, HKUST

LLM Serving LLM Inference LLM Inference Scheduling

Apr 30, 2026cs.NI

Rethinking Network Topologies for Cost-Effective Mixture-of-Experts LLM Serving

Mixture-of-experts (MoE) architectures have turned LLM serving into a cluster-scale workload in which communication consumes a considerable portion of LLM serving runtime. This has prompted industry to invest heavily in expensive high-bandwidth scale-up networks. We question whether such costly infrastructure is strictly necessary. We present the first systematic cross-layer analysis of network cost-effectiveness for MoE LLM serving, comparing four representative XPU (e.g., GPU/TPU) topologies (scale-up, scale-out, 3D torus, and 3D full-mesh). We find that lower-cost switchless topologies are more cost-effective than the scale-up topology across all serving scenarios explored, improving cost-effectiveness by 20.6-56.2%. In particular, the 3D full-mesh topology is Pareto-optimal in terms of the performance-cost tradeoff. We also find that current scale-up link bandwidths are over-provisioned: reducing the link bandwidth improves throughput per cost by up to 27%. A forward-looking analysis of upcoming GPU generations indicates that the cost-performance advantage of switchless networks will likely persist.

Junsun Choi, Sam Son, Sunjin Choi +5

UC Berkeley · UC Berkeley & ICSI

LLM Serving Cost-Aware Inference Mixture-of-Experts Inference

Apr 29, 2026cs.DC

FaaSMoE: A Serverless Framework for Multi-Tenant Mixture-of-Experts Serving

Mixture-of-Experts (MoE) models offer high capacity with efficient inference cost by activating a small subset of expert models per input. However, deploying MoE models requires all experts to reside in memory, creating a gap between the resource used by activated experts and the provisioned resources. This underutilization is further pronounced in multi-tenant scenarios. In this paper, we propose FaaSMoE, a multi-tenant MoE serving architecture built on Function-as-a-Service (FaaS) platforms. FaaSMoE decouples the control and execution planes of MoE by deploying experts as stateless FaaS functions, enabling on-demand and scale-to-zero expert invocation across tenants. FaaSMoE further supports configurable expert granularity within functions, trading off per-expert elasticity for reduced invocation overhead. We implement a prototype with an open-source edge-oriented FaaS platform and evaluate it using Qwen1.5-moe-2.7B under multi-tenant workloads. Compared to a full-model baseline, FaaSMoE uses less than one third of the resources, demonstrating a practical and resource-efficient path towards scalable MoE serving in a multi-tenant environment.

Minghe Wang, Trever Schirmer, Mohammadreza Malekabbasi +1

TU Berlin · Berlin, Germany

Mixture-of-Experts Language Models LLM Serving Mixture-of-Experts Inference LLM Inference Serving Cloud Computing