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

Jun 25, 2026cs.PF

Cluster, Route, Escalate: Cascaded Framework for Cost-Aware LLM Serving

Efficient deployment of large language models (LLMs) in production forces a trade-off between accuracy and cost. Operators often default to a single model that is either expensive for easy queries or insufficient for hard ones. To address this challenge, we propose a two-stage cascaded solution. Stage 1 clusters incoming queries and assigns each cluster to its most cost-effective model. The cost budget for this routing process is set by an interpretable hyperparameter, tuned offline. Stage 2 adds a quality estimation (QE) cascade; when an output from Stage 1 is judged low-quality, the query is escalated to a stronger model. This ensures only hard or low-confidence cases reach the expensive models. On the test datasets, the cascaded system retains 97-99% of the strongest model's accuracy while reducing Time Per Output Token (TPOT). It requires only task-correctness labels and adapts to changes in the model pool without manual reconfiguration.

Yasmin Moslem, Magdalena Kacmajor, Vasudevan Nedumpozhimana +11

1ADAPT Centre, Trinity College Dublin · 2Huawei Research

LLM Serving Cost-Aware Inference LLM Routing

Jun 25, 2026cs.LG

PersistentKV: Page-Aware Decode Scheduling for Long-Context LLM Serving on Commodity GPUs

Autoregressive large language model (LLM) serving is increasingly limited by key-value (KV) cache movement rather than dense matrix multiplication. Modern paged-attention systems reduce fragmentation, and mature kernels like FlashInfer provide highly optimized decode attention. However, the best single-kernel implementation is not always the best serving schedule: low-active long-context decode can under-utilize GPUs, while mixed sequence lengths introduce tension between many exact-length launches and coarse padded batches. We present PersistentKV, a native block-table decode attention engine and page-aware scheduling study for grouped-query attention (GQA). PersistentKV maps work by KV-head group, executes directly over native page tables, and adds a compact workqueue schedule executing only non-empty row-KV-head-sequence-split tasks. On an RTX 3060 (FP16, page size 16, Hq=32, Hkv=8, d=128), a calibrated roofline-style policy selects FlashInfer for small active batches, PersistentKV sequence splitting for batch size 1 (B1) long-context steps, and PersistentKV workqueue scheduling for supported B8 long-context GQA steps. With cost-model constants fixed on calibration traces, five held-out seeds improve mean wall decode-token throughput by 1.04x to 1.08x on B8 bimodal, uniform, and Zipf-like workloads, and by 1.40x on a B1 bucketed trace. For the B4 boundary case and uncalibrated GQA ratios, the policy avoids regressions by routing to FlashInfer. We also report an attention-plus-MLP timing proxy and workload counters showing workqueue scheduling reduces launch fan-out from 16.00 to 2.00 launches per step on held-out bimodal B8. These results show that work assignment is a decisive serving-system variable.

Muhammad Ahmed

LLM Serving GPU Kernel Optimization KV Caching Long-Context Language Model Inference LLM Inference Acceleration

Jun 23, 2026cs.DC

CrossPool: Efficient Multi-LLM Serving for Cold MoE Models through KV-Cache and Weight Disaggregation

Emerging LLM services increasingly host many sparse MoE models, yet most models receive sparse requests and remain cold. This creates a GPU memory problem: model weights are stable and model-determined, while KV-cache is transient and demand-determined. Because cold models rarely reach peak KV-cache demand at the same time, reserving worst-case KV capacity per model wastes memory; a shared KV-cache pool can instead provision aggregate active demand. However, KV-cache sharing is not sufficient when weights and KV-cache remain in a monolithic GPU memory pool. Static weights compete with dynamic KV-cache, and KV-head-limited attention under cold, low-concurrency traffic exposes only a fraction of replicated KV capacity, leading to low GPU memory utilization and weak long-context support. We present CrossPool, a serving engine for cold MoE models that separates FFN weights and KV-cache into two GPU memory pools: a weights pool that consolidates FFN weights across cold models, and a KV-cache pool that dynamically serves active requests while keeping attention local to KV-cache. CrossPool combines a KV-cache planner and virtualizer, a layer-wise pipeline scheduler that hides hidden-state transfers, and persistent kernels with control lowering to reduce CPU-GPU control overhead. With efficient GPU memory pooling, CrossPool underpins bursty long-context requests and outperforms the state-of-the-art kvcached-based multi-LLM serving system, reducing P99 TBT by up to 10.4x.

Zhuoren Ye, Tianyu Wo, Dinghao Xue +4

School of Software, Beihang University

Mixture-of-Experts Language Models LLM Serving KV Caching KV-Cache Management

Jun 22, 2026cs.CR

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

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

Yinpeng Wu, Yitong Chen, Lixiang Wang +3

Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University

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

Jun 21, 2026cs.AI

Geometry-Aware Online Scheduling for LLM Serving: From Theoretical Bound to System Practice

The rapid growth of interactive Large Language Model serving has made efficient management of dynamic Key-Value cache footprints increasingly important for inference performance. Modern inference systems overwhelmingly rely on time-centric scheduling heuristics, such as Shortest Job First. However, their classical guarantees are rooted in traditional scheduling modeling, failing to capture the highly dynamic, 2D spatio-temporal geometric growth specific to LLM inference mechanisms. To resolve this, we propose the geometry-aware online scheduling by introducing the Smallest Volume First (SVF) algorithm and its highly efficient variant, 1-bit SVF. Via a novel volume-certificate proof, we establish a worst-case approximation ratio for SVF that approaches \textbf{3} in the high-concurrency regime of LLM serving, substantially improving upon the prior best constant of 48. Building upon this core breakthrough, we complete a comprehensive theoretical taxonomy analyzing our algorithms across different traffic scenarios and information availability. Practically, we seamlessly integrate our approach as a plug-and-play layer in vLLM. Extensive evaluations on Llama-3.1 models demonstrate comprehensive performance gains: SVF delivers strong reductions in both average and tail latency, while 1-bit SVF, with merely a single bit of information, achieves competitive throughput and latency. This work establishes a theoretically sound and empirically proven approach for resolving memory-constrained scheduling in modern LLM deployments. To facilitate future research, our code is available at https://github.com/Li-Beverly-Kong/Geometry-Aware-Online-Scheduling.git.

Li Kong, Qi Qi, Yinyu Ye +1

Gaoling School of Artificial Intelligence Renmin University of China Beijing, China · Department of Management Science and Engineering Stanford University Stanford, CA 94305-4026 · Department of Industrial Engineering and Decision Analytics HKUST Hongkong, China

LLM Serving LLM Inference Scheduling KV-Cache Management Memory-Efficient Inference LLM Request Scheduling

Jun 19, 2026cs.DC

Recency/Frequency Adaptive KV Caching for Large Language Model Serving

Key-value (KV) caching is a powerful technique for accelerating large language model inference and generation. Inference workloads are large and diverse, which makes them difficult to cache effectively. Existing cache management strategies adopt the least-recently-used policy for evicting cache blocks. However, LRU leads to multiple unrelated workloads flushing each other's caches. To address this, we integrate adaptive caching that dynamically allocates cache space between recently and frequently occurring KV blocks. Evaluations show that it improves the KV cache hit rate by up to 10.8% and reduces time to first token by up to 12.6% over naive vLLM on synthetic document question answering workloads, and 2.1% and 2.0% respectively on real-world conversation workloads. The method generalizes well to batch inference and demonstrates clear interpretability while effectively accommodating diverse workloads.

Yang Shen, Meghana Madhyastha, Robert Underwood +2

Department of Computer Science, Johns Hopkins University, Baltimore, USA

LLM Serving KV Caching KV-Cache Eviction KV-Cache Management LLM Inference Acceleration

Jun 18, 2026cs.SE

Token-Operations-Oriented Inference Optimization Techniques for Large Models

Large model inference optimization serves as a key foundation for supporting the scalable, low-cost, and highly stable operation of large model services. Centered on token-oriented inference optimization technology, this paper proposes for the first time a four-layer technical architecture consisting of Multi-model Fusion, Model Optimization, Compute-Model Fusion, and Compute-Network-Model Fusion. It systematically reviews the key technologies and current industry status across these four levels and analyzes the application value of related technologies in real-world business scenarios. This paper provides a practical technical path for reducing token production costs, improving token service efficiency, ensuring the stability of token supply, and driving the transition of large model services from being merely callable to being operable.

Shiguo Lian, Kai Wang, Zhaoxiang Liu +22

Unicom Data Intelligence, China Unicom · Data Science and Artificial Intelligence Research Institute, China Unicom · Tsinghua University +7

LLM Serving Inference-Time Optimization Cost-Aware Inference LLM Inference Acceleration

Jun 16, 2026cs.LG

Beyond Prediction: Tail-Aware Scheduling for LLM Inference

LLM serving exhibits extreme length variability, making size-based scheduling difficult in practice. Recent LLM schedulers approximate SJF/SRPT using predicted decode lengths or ranks and primarily report mean-centric metrics such as TTFT and TBT. We show that these prediction-driven policies can be fragile under distribution shifts, bursty arrivals, and GPU memory pressure, while offering limited control over the tail latency (P90-P99) that dominates user experience, even with perfect decode-length knowledge. We introduce a distribution-aware, prediction-free scheduling framework that replaces explicit length prediction with soft priority boosting driven by lightweight statistical signals. Our design co-optimizes scheduling and cache-aware preemption to account for memory-coupled decode dynamics across workload mixes. Evaluated on production and open-source traces, our method reduces P99 TTLT by up to 35-50% relative to SRPT with perfect length knowledge and reduces TTFT by 34-47% across workloads, including reasoning-heavy and chat-heavy tasks. These results demonstrate a robust alternative for optimizing tail latency in online LLM serving.

Yueying Li, Yuanfan Chen, Jiayang Chen +6

Cornell University, Computer Science Department, NY, USA · Microsoft Azure System Research, WA, USA · Cornell University, Electrical and Computer Engineering Department, NY, USA +2

LLM Serving Inference-Time Optimization LLM Inference Scheduling LLM Request Scheduling

Jun 14, 2026math.OC

Service-Induced Congestion in Memory-Constrained LLM Serving

In large language model (LLM) serving, each request accumulates persistent graphics processing unit (GPU) memory during service as its key-value cache grows with every generated token. Under high concurrency, aggregate memory usage therefore increases endogenously over time: the service process itself creates future capacity pressure. When memory capacity is exceeded, systems evict active requests, discarding cached state and restarting them later, which wastes computation and reduces throughput. We develop a discrete-time dynamical model of memory-constrained LLM inference that captures admission, memory growth, and eviction under continuous batching. In the saturated-input regime, the system admits both eviction-free fixed points and limit cycles with evictions. For homogeneous workloads, we show that the eviction-free equilibrium is unstable and that, except for a Lebesgue-measure-zero exact-capture set, the system converges to a unique worst-case limit cycle that is asymptotically stable outside this exceptional set, with throughput losses as large as 50%. For heterogeneous workloads, we prove a stability criterion in the two-class common-input setting and explain how the survival-polynomial mechanism generalizes to multiple classes and heterogeneous-input lengths. Under an input-dominated scaling regime, coprime decoding lengths stabilize the eviction-free equilibrium, while non-coprime lengths create synchronized modes that drive instability. These results characterize when workload heterogeneity desynchronizes completions and helps stabilize memory-constrained serving. More broadly, we identify service-induced congestion as a structural instability mechanism and derive scheduling design principles for sustaining high throughput.

Ruicheng Ao, Jing Dong, Gan Luo +1

Institute for Data, Systems, and Society, Massachusetts Institute of Technology, Cambridge, MA 02139 · Columbia Business School, Columbia University, New York, NY 10027 · School of Mathematical Sciences, Peking University, Beijing, China

LLM Inference Efficiency LLM Serving

Jun 13, 2026cs.LG

Director: Accelerating Distributed MoE Serving via Online Proactive Expert Placement

Expert parallelism has become the prevailing paradigm to serve Mixture-of-Experts (MoE) models. Its efficiency depends on the communication and computation latencies of the GPUs, which are linked to the placement of experts in the GPUs. Existing works for optimizing expert placement focus on leveraging past requests' expert activation patterns. However, they demonstrate deficiencies facing diverse and rapidly changing request patterns, calling for an online, proactive approach. Implementing such an approach requires addressing several challenges: the uncertainty associated with incoming requests' expert activation, the cost of expert migration, and the NP-hard complexity in optimization. Therefore, we present Director, a new distributed MoE serving system that minimizes end-to-end latency via prediction-driven, online expert placement. Director uses either a lightweight cascaded predictor or a low-bit quantized replica for expert activation patterns of incoming requests. An online migration module then enacts the changes with near-zero downtime by executing migrations in compute-bound phases, keeping disruption bounded. At its core, a relaxation-based expert placement optimizer operates under capacity constraints, runs in polynomial time, and achieves a

(1+ε)

approximation ratio. Finally, we implement a prototype and demonstrate, through extensive experiments, a reduction in end-to-end latency of

11\sim55\%

for popular MoE models (e.g., Mistral, DeepSeek and Qwen) compared to existing work.

Qianli Liu, Kaibin Guo, Zicong Hong +5

Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong · School of Software Engineering, Sun Yat-Sen University, China · School of Cyber Science and Engineering, Xi’an Jiaotong University, China +1

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

Jun 11, 2026cs.DC

STREAM: Multi-Tier LLM Inference Middleware with Dual-Channel HPC Token Streaming

Researchers and practitioners working with large language models face a fragmented landscape: local models are free and private but hardware limits the model size and context windows a researcher can use; institutional HPC centers offer powerful GPU resources at no marginal cost and keep data within institutional boundaries, but operate behind firewalls and are designed for batch jobs rather than interactive use; commercial cloud APIs provide frontier-model quality on demand but impose significant cost and data retention policies unsuitable for sensitive research data. No existing system unifies all three. STREAM (Smart Tiered Routing Engine for AI Models) addresses this gap with four contributions: (1) a three-tier routing architecture combining local, HPC, and cloud inference with a local LLM-based complexity judge; (2) a dual-channel HPC streaming architecture that separates the Globus Compute control plane (authentication and job dispatch) from a WebSocket relay data plane (token delivery), enabling sub-second TTFT (0.54 s median, 21.1x over batch mode's 11.40 s) through institutional firewalls without VPN or firewall rule changes, with end-to-end AES-256-GCM encryption ensuring the relay operator cannot read token payloads; (3) tier-aware context summarization that prevents long conversations from forcing simple queries onto expensive tiers; and (4) an HPC-as-API proxy mode that exposes HPC inference as an OpenAI-compatible endpoint callable from any standard client with no HPC expertise, a deployment pattern made practical only by the sub-second TTFT of contribution (2). Llama 3.2 3B achieves 85.1% free-tier retention on a 1,200-query benchmark spanning ten domains. Measured TTFT: 0.26 s local, 0.54 s HPC (relay), 1.68 s cloud.

Anas Nassar, Steve Mohr, Leonard Apanasevich +1

Advanced Cyberinfrastructure for Education and Research (ACER) University of Illinois Chicago Chicago, Illinois, USA

LLM Serving LLM Inference High-Performance Computing LLM Routing

Jun 10, 2026cs.SE

Characterizing Software Aging in GPU-Based LLM Serving Systems

This paper proposes an empirical methodology to study software aging in GPU-based LLM serving systems. Traditional aging studies focus on CPU-centric software with relatively regular workloads; LLM serving is different, spanning a Python host and a CUDA device, handling requests whose cost varies by orders of magnitude, and relying on rapidly evolving software stacks. We run a 216-hour campaign across six co-located deployments under identical stress conditions, monitor host, device, and client metrics in parallel, and apply a statistical pipeline that accounts for autocorrelation and multiple testing. Our results reveal statistically significant memory aging in all deployments, with leak rates strongly dependent on the serving runtime and deployment configuration. Beyond these findings, we provide a reproducible framework that opens a research direction at the intersection of the software aging and rejuvenation and LLM serving communities.

Domenico Cotroneo, Bojan Cukic

University of North Carolina at Charlotte · College of Computing and Informatics

Software Engineering LLM Serving

Jun 10, 2026cs.CL

External Experience Serving in Production LLM Systems: A Deployment-Oriented Study of Quality-Cost Trade-offs

Production LLM systems accumulate reusable operational experience, but the practical deployment issue is not merely whether such experience can help. It is how different serving strategies trade off quality against online cost under realistic constraints. Injecting external experience can improve task quality, yet it also increases prompt burden, latency, and serving pressure. We study \textit{external experience serving} as a deployment-oriented quality-cost trade-off problem. We evaluate this question in a real production moderation setting, with tool-use and GPQA as supporting contrast tasks that expose different output-cost regimes. We compare no-experience baselines, random experience controls, global prompt injection, and retrieval-based selective injection, and analyze both task quality and serving cost. The results show that, once experience becomes case-dependent, selective retrieval provides a stronger operating point than unconditional global injection. They further show that retrieval quality matters more than simply increasing Top-

K

, and that the same serving policy can exhibit substantially different cost-benefit profiles across short-output and decode-heavy regimes. These findings suggest that external experience is best treated as a selective, cost-aware serving decision rather than as a universal add-on. Overall, in the settings studied here, external experience pays off only when both the serving interface and the task-specific cost structure make its quality gains worth the online cost.

Lin Sun, Heming Zhang, Xiangzheng Zhang

Qiyuan Tech

LLM Serving Knowledge Augmentation for Language Models Cost-Aware Inference

Jun 9, 2026cs.LG

K-Forcing: Joint Next-K-Token Decoding via Push-Forward Language Modeling

Autoregressive (AR) language modeling is the dominant paradigm for text generation, yet its sequential token-by-token decoding makes inference memory-bound and inefficient. Existing acceleration approaches, such as speculative decoding and diffusion language models, can yield speedups under certain conditions but do not directly address high-load batch serving--the scenario most critical for industrial-scale deployment. We introduce K-Forcing, a push-forward language modeling paradigm for joint next-k-token decoding. K-Forcing distills an existing AR model into a conditional push-forward mapping--one that transforms independent uniform noise variables into a joint sample of multiple future tokens in a single forward pass. This design preserves fixed-length outputs, reuses the AR teacher backbone, and remains compatible with standard AR serving infrastructure. We train this mapping via progressive self-forcing distillation, which gradually expands the prediction window while enabling the student to closely match the sequence distribution of the AR teacher. We evaluate K-Forcing on LM1B and OpenWebText using a standard causal Transformer backbone. When aggressively configured to generate k = 4 tokens per forward pass, K-Forcing delivers approximately 2.4-3.5x speedup across different batch sizes, while incurring modest quality degradation relative to its AR teacher. As inference increasingly dominates the lifetime compute cost of modern LLMs, K-Forcing offers a promising route toward accelerating AR generation under real-world high-load deployment.

Zhiwei Tang, Yuanyu He, Yizheng Han +4

1DAMO Academy, Alibaba Group · 2Hupan Lab · 3Zhejiang University +1

LLM Serving Language Model Decoding Autoregressive Language Modeling LLM Inference Acceleration Language Model Distillation

Jun 8, 2026cs.CL

AGENTSERVESIM: A Hardware-aware Simulator for Multi-Turn LLM Agent Serving

Multi-turn LLM agents interleave model calls with external tool invocations, shifting serving from stateless request processing to stateful program execution. Serving these workloads requires scheduling, KV-cache management, and routing policies that use program-level context, including turn dependencies, tool-induced gaps, and reusable KV state. Evaluating such policies directly on real systems is costly, since each design point may require dedicated accelerator time across arrival rates, model scales, serving-instance counts, and memory hierarchies. Simulation offers a scalable alternative, but existing LLM serving simulators target stateless request-level workloads and therefore omit the core dynamics of agent serving: multi-turn program execution, cross-turn cache locality, and KV-cache residency during tool gaps. We present AGENTSERVESIM, a hardware-aware simulator for multi-turn LLM agent serving. AGENTSERVESIM evaluates serving policies at program granularity through composable modules: a Program Orchestrator preserves program identity and turn order, a Tool Simulator materializes tool-induced gaps, a Session-Aware Router maintains program-to-instance affinity for cache-aware dispatch, and a KV Residency Model tracks policy-defined KV placement across HBM, host DRAM/CXL, and eviction. Across real serving deployments and hardware configurations, AGENTSERVESIM reproduces real-system behavior within 6% error across key performance metrics while running entirely on commodity CPUs. These results show that AGENTSERVESIM enables controlled, repeatable exploration of agent-serving policies without requiring exhaustive deployment on costly accelerators.

Rakibul Hasan Rajib, Mengxin Zheng, Qian Lou

University of Central Florida

LLM Serving KV-Cache Management LLM Inference Serving LLM Agent Serving

Jun 5, 2026cs.LG

Semantic Cache Distillation: Efficient State Transfer via Reuse and Selective Patching

Disaggregated serving alleviates memory bottlenecks in Large Language Model (LLM) inference but creates a severe communication bottleneck: transmitting high-dimensional Key-Value (KV) caches often dominates time-to-first-token (TTFT). Moreover, reusing caches across heterogeneous models (e.g., base and fine-tuned variants) causes semantic misalignment that accumulates over layers, degrading generation quality. We propose Semantic Cache Distillation (SCD), a loss-constrained framework that replaces raw KV transmission with compact semantic codes. SCD addresses these challenges via two mechanisms: (1) Reuse, which reconstructs most layers from low-rank subspaces to minimize transfer cost, and (2) Patch, which predicts normalized inputs at sparse transition layers to truncate error propagation. Empirically, SCD delivers up to 2.65

\times

TTFT speedup over the oracle consumer prefill and dominates quantization and selective recomputation baselines on the quality--latency Pareto frontier in bandwidth-constrained regimes, while keeping generation quality within 5% F1 of the oracle.

Qianli Ma, Zhiqing Tang, Hanshuai Cui +2

Faculty of Arts and Science, Beijing Normal University, Zhuhai 519087, China · Institute of Artificial Intelligence and Future Networks, Beijing Normal University, Zhuhai 519087, Guangdong, China · School of Artificial Intelligence, Beijing Normal University, Beijing 100875, China +1

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

Jun 4, 2026cs.AR

SPEAR: A System for Post-Quantization Error-Adaptive Recovery Enabling Efficient Low-Bit LLM Serving

Efficient large language model (LLM) serving is increasingly constrained by deployment cost. Quantization is a key technique for reducing serving cost, yet even state-of-the-art 4-bit quantizers exhibit a noticeable quality gap from FP16, particularly for smaller models where low-bit serving is most beneficial. We identify a fundamental cause of this gap: quantization error is highly input-dependent and varies substantially across tokens, while existing post-quantization compensation methods are static and apply identical corrections to all inputs. As a result, easy tokens are over-corrected while hard tokens remain under-corrected. We present SPEAR, a system for post-quantization error-adaptive recovery that improves low-bit LLM serving. SPEAR introduces lightweight Error Compensators (ECs) modulated by per-token gates and places them only at the most error-sensitive layers identified through a CKA-guided entropy-aware diagnostic. This focuses a small parameter budget where it is most effective. Efficient deployment of ECs presents several systems challenges, including additional computation, tensor-parallel synchronization caused by input-dependent gating, and latency instability across configurations. SPEAR addresses these issues through adaptive kernel-fusion dispatch, combining an epilogue-integrated peer-reduction kernel with P2P dual-write to fuse the post-EC computation into low-bit GEMMs, and an SLO-constrained EC-aware scheduler for predictable serving performance. Across challenging per-channel quantization settings, SPEAR recovers 56-75% of the perplexity gap between W4 and FP16 while adding less than 1% model memory overhead and maintaining latency comparable to a widely used 4-bit serving deployment.

Hongyuan Liu, Yawei Li, Zhiqiang Que +3

University of Electronic Science and Technology of China · University of Bristol · 3ETH Zurich

LLM Quantization LLM Serving Post-Training Quantization Low-Bit Quantization Neural Network Quantization

Jun 4, 2026cs.AI

Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents

Sparse attention is becoming increasingly important for serving large language models (LLMs) as generation lengths continue to grow. However, deploying and evaluating new sparse attention algorithms at scale remains highly engineering-intensive, slowing both human researchers and AI agents in exploring the sparse attention design. To address this challenge, we present Vortex, a system that combines a Python-embedded frontend language atop a page-centric tensor abstraction for expressing a broad range of sparse attention algorithms, with an efficient backend tightly integrated into modern LLM serving stacks. Vortex enables rapid prototyping, deployment, and evaluation of sparse attention algorithms, effectively translating their theoretical efficiency gains into real-world throughput improvements. As a result, Vortex substantially accelerates the design and iteration of sparse attention algorithms. First, AI agents use Vortex to automatically generate and refine diverse algorithms, the best reaching up to

3.46\times

higher throughput than full attention while preserving accuracy. Second, Vortex extends sparse attention to emerging architectures and very large models that are otherwise hard to experiment with, reaching up to

4.7\times

higher throughput on the MLA-based GLM-4.7-Flash and

1.37\times

on the 229B-parameter MiniMax-M2.7 on NVIDIA B200 GPUs.

Zhuoming Chen, Xinrui Zhong, Qilong Feng +5

1Carnegie Mellon University · 2Rice University · 3National University of Singapore

LLM Serving LLM Inference Acceleration Sparse Attention

Jun 4, 2026cs.LG

Tangram: Unlocking Non-Uniform KV Cache Compression for Efficient Multi-turn LLM Serving

Multi-turn LLM serving accumulates dialogue history whose Key-Value (KV) cache grows with every turn and every user, quickly exceeding the model weights themselves and making memory -- not compute -- the binding constraint on throughput. Non-uniform KV compression, which allocates heterogeneous budgets across attention heads, preserves accuracy far better than uniform schemes, yet remains impractical: modern serving stacks assume identical KV lengths across heads, so heterogeneity traps freed memory as page fragmentation, spends up to 25% of prefill time reclaiming scattered pages, and skews GPU workloads that inflate decode latency by up to

1.7\times

or burn 15--20% of each decode step on re-planning. We observe that this heterogeneity need not be discovered at runtime: head-wise retention follows a two-level structural regularity -- an input-invariant head ranking with narrowly bounded per-head ratios -- that can be calibrated offline from as few as 50 samples. Building on this insight, we present Tangram, a serving framework that statically resolves what prior systems handle dynamically: Budget Reservation fixes each head's post-compression footprint at scheduling time, eliminating page reclamation; Ragged Paging clusters similar-budget heads into independent page tables, turning fragmentation into reclaimable memory; and Ahead-of-Time Load Balancing precomputes balanced GPU partitions with zero runtime planning. Implemented on vLLM, Tangram serves as a drop-in substrate for existing non-uniform compression methods, matching their accuracy while improving end-to-end throughput by up to

2.6\times

over the full-KV baseline. Our implementation is publicly available at https://github.com/aiha-lab/TANGRAM.

Hyungmin Kim, Minsoo Kim, Hongseok Kim +1

LLM Serving KV Caching Memory-Efficient Optimization LLM Inference Acceleration KV-Cache Compression

Jun 4, 2026cs.AI

RedKnot: Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention

As the input length of large language model (LLM) serving continues to grow, the KV cache has become a dominant bottleneck in AI infrastructure. It limits GPU memory capacity, serving concurrency, cache reuse, and distributed scalability. Multiple important problems, including position-independent KV cache, prefix KV cache compression, hot/cold KV cache separation, and distributed KV cache management, all depend on how the KV cache is represented and managed. However, existing serving systems largely rely on a monolithic KV cache abstraction, where the KV cache is treated as a homogeneous sequence of token-level memory blocks and managed with similar policies across attention heads and serving scenarios. We observe that KV cache utility is highly structured across KV heads: different heads exhibit different functional roles, attention distances, and runtime importance. Therefore, a full KV cache is not always necessary for every head, token range, or serving scenario. We present RedKnot, a head-aware KV cache management system for LLM serving. RedKnot breaks the conventional monolithic KV cache abstraction by decomposing the KV cache along KV heads, whose importance and effective attention ranges vary significantly across serving scenarios. This head-level decomposition turns the KV cache from a monolithic tensor abstraction into a structured memory object, enabling RedKnot to uniformly support position-independent KV reuse, prefix KV compression, hot/cold KV separation, and distributed KV placement while preserving output fidelity and improving resource efficiency, without requiring model retraining or fine-tuning. RedKnot establishes a new foundation for AI infrastructure by transforming the KV cache from a monolithic, passive runtime artifact into a dynamic, model-aware runtime substrate for scalable LLM serving.

Yang Liu, ZhaoKai Luo, HuaYi Jin +5

†Xiaohongshu Inc., China · ¶Huawei Cloud · §Peking University

LLM Serving KV Caching KV-Cache Management KV-Cache Reuse KV-Cache Compression

Jun 3, 2026cs.DC

Ekka: Automated Diagnosis of Silent Errors in LLM Inference

LLM serving frameworks are quickly evolving with a complex software stack and a vast number of optimizations. The rapid development process can introduce silent errors where output quality silently degrades without any explicit error signals. Diagnosing silent errors is notoriously difficult due to the substantial semantic gap between the high-level symptoms and the low-level root causes. We observe that diagnosis of silent errors can be effectively framed as a differential debugging problem by leveraging the existence of semantically correct reference implementations. We propose Ekka, an automated diagnosis system that identifies root causes by systematically aligning and comparing intermediate execution states between a target and a reference framework. We constructed a benchmark of real-world silent errors from popular serving frameworks, where Ekka shows 80% pass@1 diagnosis accuracy and 88% pass@5 diagnosis accuracy, outperforming state-of-the-art systems. Ekka also diagnoses 4 new silent errors from serving frameworks, all of which have been confirmed by the developers.

Yile Gu, Zhen Zhang, Shaowei Zhu +4

University of Washington · 2Amazon Web Services.

Software Engineering LLM Serving Language Model Error Detection Root Cause Analysis Differential Diagnosis Fault Diagnosis

Jun 2, 2026cs.DC

E2LLM: Towards Efficient LLM Serving in Heterogeneous Edge/Fog Environments

Large Language Models (LLMs) have become integral to modern applications, yet their deployment remains challenging. Beyond executing the models themselves, practical deployment must address cost efficiency, low latency, and optimal resource utilization. Conventional approaches typically assume that an entire model can be hosted on a single device, which does not hold in many real-world scenarios, particularly in Edge and Fog environments where device resources are constrained. In this paper, we introduce E2LLM, a framework designed to enable efficient LLM deployment in such resource limited settings. Rather than simply partitioning a single model across all available devices, E2LLM replicates the full model across multiple groups of devices (replicas) and applies model parallelism within each replica. Each replica is assigned a specialized role PREFILL or DECODER based on its efficiency in handling input and output tokens. This separation leverages the inherent differences between these two phases of LLM inference. To effectively organize devices, we utilize a Genetic Algorithm to form clusters that maximize system performance. Within each cluster, we apply Dynamic Programming to determine an optimal partitioning strategy that minimizes bottlenecks in model-parallel execution. Experimental results demonstrate that our approach adapts robustly to varying workloads, including scenarios with significant variation in input and output token lengths. Compared to the Splitwise baseline, E2LLM reduces average waiting time by over 50% under high-demand conditions

Truong-Thanh Le, Amir Taherkordi, Hoang-Loc La +3

Department of Informatics University of Oslo Oslo, Norway · Department of Computer Science UiT The Arctic University of Norway Tromsø, Norway

LLM Serving Edge Computing LLM Inference Acceleration

Jun 1, 2026cs.DC

Observation, Not Prediction: Conversation-Level Disaggregated Scheduling for Agentic Serving

LLM-based agents resolve a user task through many turns of dependent inference and tool calls, producing a workload whose total cost is unknown when the task arrives. Existing multi-turn systems keep the turn as the scheduling unit and decide, turn by turn, whether to disaggregate prefill from decode. That decision rests on the turn's decode length, tool behavior, and KV growth, quantities that are not observable when the scheduler must act, forcing the system to predict them. We show this dependence on prediction is imposed by the scheduling unit, not the workload. Raising the scheduling unit from the turn to the conversation converts turn-level irregularity into a stable, two-phase structure: 1) a compute-bound turn-1 prefill followed by 2) a long, memory-bound tail. Thus, with the conversation as the scheduling unit, placement reduces to reading the first-turn input length and per-decoder KV occupancy, both directly observable. We instantiate this principle in ConServe, which routes the first-turn prefill to a high-throughput prefiller, transfers the KV cache exactly once, and pins the conversation to a single decoder for its entire tail, with no learned model of decode-side cost. Against a per-turn prediction baseline, ConServe reduces p95 time-to-first-effective-token (the latency of a conversation's first user-visible output) by 51.08% and improves energy efficiency by 7.51% while preserving last-turn TBT and SLOs; mapping the two phases onto heterogeneous GPU tiers adds a further 22.75% in energy efficiency.

Jianru Ding, Ryien Hosseini, Pouya Mahdi Gholami +2

University of Chicago

LLM Serving Disaggregated LLM Serving LLM Inference Serving LLM Agents

May 27, 2026cs.LG

Inference-Native Zeroth-Order Optimization for LLMs

Zeroth-order (ZO) methods train large language models using only forward passes, yet common ZO execution paths perform substantial work beyond what the algorithm itself requires. To remove this extra execution overhead, we present Infer-ZO, which separates the evaluations required by the algorithm from how they are executed, allowing them to reuse existing inference-engine optimizations. After removing inherited execution work, a complete Infer-ZO step on Qwen3-14B adds only 1.16% wall-clock time over matched inference, bringing ZO execution close to its fundamental inference workload. With Infer-ZO, ZO evaluations run at near-inference cost with frozen base weights and can share GPU batches with ordinary inference requests. In co-serving experiments, foreground and background throughput remain within 1-3% of the corresponding background-request baseline. Across 15 Qwen3, Llama, and OPT models, Infer-ZO achieves 2.10x-9.94x end-to-end step speedups over released LoZO. Code is available at https://github.com/playeriv65/zo-vllm.

Zelin Li, Caiwen Ding

University of Minnesota

LLM Serving Zeroth-Order Optimization Efficient Language Model Training LLM Inference Acceleration

May 27, 2026cs.LG

How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving

Modern large language model (LLM) inference has progressively disaggregated to keep pace with growing model sizes and tight TTFT and TPOT service-level objectives: from chunked-prefill aggregation, to prefill-decode (P/D) disaggregation, and most recently to operator-level Attention-FFN Disaggregation (AFD). This trend is especially important for mixture-of-experts (MoE) models, where memory-bound attention, compute-intensive expert FFNs, and MoE dispatch/combine communication create distinct resource demands. AFD further exposes this heterogeneity by placing attention and MoE-FFN execution on separate GPU groups. Each level of disaggregation deepens the scheduling design space across workload characteristics, resource allocation, and interconnect topology, raising the central question: when does each level actually pay off? We systematically characterize this trade-off for MoE inference across realistic workloads spanning input/output sequence lengths, prefix-KV reuse, and per-user latency constraints. Using chunked-prefill and P/D disaggregation as baselines, we study the benefits and limits of AFD at scale through a framework that fuses on-device kernel measurements with high-fidelity network simulation. Under strict TTFT/TPOT SLOs, AFD sustains around 4k tokens/s of system throughput on DeepSeek-V3.2 across chat, coding, and agentic-coding workloads, where non-AFD deployments are infeasible. We distill concrete takeaways for jointly optimizing throughput and interactivity, including how to partition attention and FFN across GPUs as a function of workload and model architecture, providing design principles for current rack- and cluster-scale deployments as well as future disaggregated AI infrastructure.

Hanjiang Wu, Abhimanyu Rajeshkumar Bambhaniya, Sarbartha Banerjee +9

1Georgia Institute of Technology · 5Infravana · 2Intel +2

LLM Serving LLM Inference Disaggregated LLM Serving Mixture-of-Experts Inference Distributed Inference

May 27, 2026cs.LG

RW-TTT: Batched Serving for Request-Owned Test-Time Training State

Test-time training (TTT) adapts an LLM during generation by reading and updating request-owned state, such as fast weights, low-rank deltas, or streaming learner state. This breaks batched LLM serving, which assumes shared static weights: serial execution is correct but slow, while naive batching can corrupt request state. We formulate this problem as read-write TTT serving and present RW-TTT , which tags each decode step with its owner, version, and READ/WRITE effect, batches only compatible phases, and commits updates only to the owner. On one GPU with eight fast-weight InPlace-TTT streams, RW-TTT reaches 274.61 aggregate tok/s, 9.31x over sequential serving and 3.44x over per-stream replicas under the same memory budget. It preserves behavior on RULER, a long-context benchmark, and passes owner/version checks.

Jian Yang, Zhizhuo Kou, Yao Tian +4

1The Hong Kong University of Science and Technology · 2The Chinese University of Hong Kong · 3National University of Singapore

LLM Serving Test-Time Optimization LLM Inference Acceleration Test-Time Training

May 26, 2026cs.AI

A Policy-Driven Runtime Layer for Agentic LLM Serving

Multi-agent LLM systems have become the dominant production workload, but the serving stack was not built for them. The agent framework above knows agent identities, role, schemas, and dispatch structure but never sees an engine-level event; the serving engine below sees every event but knows nothing about agents. A surprising number of cross-cutting policies depend on both: prefix caching, batch shaping, speculative execution, fairness, tool-result memoization, safety enforcement, and more. Each lives in the seam between the two layers and is currently solved by a one-off patch into one neighbor or the other. We argue this seam is best addressed by an architectural change rather than point fixes: insert a third tier, an agent runtime layer, between the framework and the engine, exposing four primitives (observe, score, predict, act) into which any agent-aware policy plugs, with agent identity as the shared coordinate. We map nine concrete policies onto the layer and validate the abstraction in depth on the one with the largest immediate serving-cost lever: KV caching across sessions, instantiated as CacheSage, which learns the per-workload agent transition matrix online and uses it for survival-based eviction and between-step prefetch. Preliminary results on five real multi-agent workloads show +13 to +37 pp cache hit-rate lift, 12% to 29% lower mean TTFT, and 6% to 14% higher throughput over an unmodified serving stack.

Rui Zhang, Chaeeun Kim, Liting Hu

University of California, Santa Cruz

LLM Inference Efficiency Multi-Agent LLM Systems LLM Serving KV-Cache Management LLM Inference Serving LLM Agent Serving

May 26, 2026q-bio.OT

BIRDS: Characterizing and Understanding Biodiversity Impact of Large Language Model Serving

Large language model (LLM) serving creates environmental impacts beyond carbon and water, including ecosystem damage through biodiversity-related pathways. We present BIRDS, a framework for Biodiversity Impact of Request-Driven LLM Serving. BIRDS defines request-level functional units, quantifies operational and embodied biodiversity impact, and introduces Quality-Normalized Biodiversity Impact (QNBI) to jointly analyze ecological impact and response quality. Across diverse workloads, models, GPUs, and regions, BIRDS reveals that biodiversity impact accumulates at scale and exposes actionable quality-aware serving tradeoffs.

Tianyao Shi, Yi Ding

Purdue University

LLM Serving Responsible AI

May 25, 2026cs.DC

Fine-Tuning and Serving Gemma 4 31B on Google Cloud TPU: A Technical Comparison with GPU Baselines

We present the first end-to-end demonstration of fine-tuning and serving Google's Gemma 4 31B model on TPU hardware, providing an empirical comparison of TPU and GPU platforms for large language model adaptation. Using LoRA on a Google TPU v5p-8 for training and TPU v6e-8 (Trillium) for inference, we document the full set of code-level adaptations required to port a GPU-native training recipe - built on PyTorch, HuggingFace TRL, and FSDP - to the JAX + Tunix/Qwix stack. These adaptations span mesh configuration, LoRA module naming conventions, sharding annotation corrections, gradient checkpoint, data pipeline restructuring, and a custom Orbax-to-safetensor checkpoint merging procedure. For inference, we detail the vLLM-TPU Docker setup necessary to serve Gemma 4 on v6e-8 and characterize the resulting latency and throughput profile. Compared with a similar-costing 2xH100 GPU baseline under identical hyperparameters, TPU training completes 1.61x faster at 2.12x lower cost. For inference, we cover the vLLM-TPU Docker setup required to serve Gemma 4 on v6e-8 and explain the observed latency and throughput characteristics across a QPS sweep spanning 512 to 16k input tokens. Across both workloads we compare performance and cost against a 2xH100 GPU baseline running identical hyperparameters. The TPU completes training 1.61x faster at 2.12x lower cost. For inference, TPU v6e-8 matches GPU at short context (<=2048 tokens) and decisively outperforms at long context: 66% higher throughput and 23.6x faster TTFT at 4096-token inputs (61 ms vs 1,443 ms at QPS=4). Our work removes a critical gap in the open tooling ecosystem and provides practitioners with a recipe for Gemma 4 Dense 31B deployment on the TPU infrastructure.

Jatin Kishnani, Mayank Goel, Amit Singh +2

AI Accelerator Inference LLM Serving LLM Fine-Tuning LLM Inference Acceleration

May 23, 2026cs.LG

ReLoRA: Knowledge-Reusing Adaptation for Fast Rollout of Evolving LLM Services

Large Language Models (LLMs) are increasingly deployed as continuously evolving services, where frequent base-model updates may invalidate previously deployed task-specific Low-Rank Adaptation (LoRA) adapters. For service providers managing numerous downstream model services, retraining each LoRA adapter from scratch for every updated base model is computationally prohibitive and delays service rollout. Meanwhile, the simpler alternative, i.e., naively applying the original LoRA adapter to the updated base model, often leads to degraded service quality due to adapter-backbone incompatibility. To address this problem, we propose ReLoRA, a knowledge-reusing re-adaptation framework that efficiently restores service-ready LoRA adapters for evolving LLM services while preserving or improving task performance. Specifically, ReLoRA comprises two key optimization steps: 1) Adaptive LoRA initialization leverages Bayesian optimization to construct a compatibility-aware starting point by fusing information from both the previously deployed task adapter and the base model's evolution; 2) Fine-tuning with scheduled regularization first rapidly steers the adapter to a high-quality region via strong regularization, followed by relaxed regularization for task-specific refinement. This design enables rapid service-quality recovery with reduced re-adaptation overhead. Extensive experiments demonstrate that ReLoRA reduces time-to-readiness by up to 8.9

\times

and improves accuracy by up to 4.6% compared to baselines.

Yang Xu, Zihuai Xu, Hongli Xu +3

Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, Jiangsu, China, 215123

LLM Serving LLM Fine-Tuning Low-Rank Adaptation