Daily Papers

Serving systems for Large Language Models (LLMs) are often optimized to improve quality of service (QoS) and throughput. However, due to the lack of open-source LLM serving workloads, these systems are frequently evaluated under unrealistic workload assumptions. Consequently, performance may degrade when systems are deployed in real-world scenarios. This work presents BurstGPT, an LLM serving workload with 10.31 million traces from regional Azure OpenAI GPT services over 213 days. BurstGPT captures LLM serving characteristics from user, model and system perspectives: (1) User request concurrency: burstiness variations of requests in Azure OpenAI GPT services, revealing diversified concurrency patterns in different services and model types. (2) User conversation patterns: counts and intervals within conversations for service optimizations. (3) Model response lengths: auto-regressive serving processes of GPT models, showing statistical relations between requests and their responses. (4) System response failures: failures of conversation and API services, showing intensive resource needs and limited availability of LLM services in Azure. The details of the characteristics can serve multiple purposes in LLM serving optimizations, such as system evaluation and trace provisioning. In our demo evaluation with BurstGPT, frequent variations in BurstGPT reveal declines in efficiency, stability, or reliability in realistic LLM serving. We identify that the generalization of KV cache management, scheduling and disaggregation optimizations can be improved under realistic workload evaluations. BurstGPT is publicly available now at https://github.com/HPMLL/BurstGPT and is widely used to develop prototypes of LLM serving frameworks in the industry.

Deploying modern Speech Language Models (SpeechLMs) in streaming settings requires systems that provide low latency, high throughput, and strong guarantees of streamability. Existing systems fall short of supporting diverse models flexibly and efficiently. We present VoxServe, a unified serving system for SpeechLMs that optimizes streaming performance. VoxServe introduces a model-execution abstraction that decouples model architecture from system-level optimizations, thereby enabling support for diverse SpeechLM architectures within a single framework. Building on this abstraction, VoxServe implements streaming-aware scheduling and an asynchronous inference pipeline to improve end-to-end efficiency. Evaluations across multiple modern SpeechLMs show that VoxServe achieves 10-20x higher throughput than existing implementations at comparable latency while maintaining high streaming viability. The code of VoxServe is available at https://github.com/vox-serve/vox-serve.

LAPS identifies and disaggregates requests with different prompt lengths in LLM serving to reduce TTFT latency. While recent systems have decoupled the prefill and decode stages to improve throughput, they still rely on unified scheduling policies that fail to adapt to heterogeneous workload characteristics. We observe that prompt-length variations lead to distinct performance bottlenecks, motivating an adaptive scheduling strategy. LAPS disaggregates multi-turn long-prefill requests from short-prefill ones and introduces a length-aware smart batching mechanism for short-prefill workloads. It adopts a dual-queue design that supports temporal disaggregation on a single prefill instance or spatial disaggregation across multiple instances. For short-prefill batches, a batch waiting window and CUDA Graph-based clustering mitigate interference from heterogeneous computation, reducing batching delay and lowering average latency. In real multi-turn workloads, LAPS reduces prefill latency by over 30\% compared to vanilla SGLang under prefill-decode disaggregation, and further decreases SLO violations by 28\% in multi-instance deployments with vanilla data-parallel configuration. Compared to the SGLang router with load balancing, it further lowers SLO violations by 12\% in multi-GPU settings. Under high concurrency and mixed-request scenarios, LAPS improves request throughput by 35\% serving Qwen2.5-32B model for prefill instance, demonstrating its effectiveness in optimizing heterogeneous LLM serving workloads.

We are entering a new era of composite model architectures that integrate diverse components such as vision encoders, language backbones, diffusion and flow heads, audio codecs, action generators, and world-model predictors. Such architectures underpin a broad class of multimodal models, including unified multimodal models, omni models, speech-language models, vision-language-action policies, and world models. However, existing model serving frameworks were built on narrow assumptions about model structure, making them ill-suited to accommodate this new architectural diversity. Here we present M*, a universal serving system for efficient serving of composite AI models. M* represents models as dataflow graphs, processing requests spanning diverse modalities and tasks as traversals over these graphs. The core insight is a modular abstraction that supports arbitrary composition of model components, flexible placement onto a physical cluster, and model-agnostic optimizations within a distributed runtime. We call this abstraction the Walk Graph and show how it can concisely capture composite models from a broad range of families. We instantiate M* on representative models and find that it achieves, on average, 20% lower end-to-end latency than vLLM-Omni for text-to-image workloads on BAGEL, while delivering up to 2.9x lower real-time factor and 2.7x higher throughput for text-to-speech workloads on Qwen3-Omni. M* also outperforms the V-JEPA 2-AC rollout baseline for robotic planning by up to 12.5x. Thus, our work paves the road towards more efficient serving of complex models with minimal developer effort.

Large language model (LLM) routing distributes inference work across different models, advancing the cost-quality Pareto frontier of LLM serving. While coarse-grained routing at the session or query level has been widely adopted in production systems, recent algorithmic work shows that fine-grained token-level routing can yield substantial efficiency and quality gains. However, efficiently serving token-level routed inference poses significant challenges to existing systems. Built on single-LLM assumptions, current systems suffer from severe step desynchronization and frequent batch admission delays under token-level routing, and they also impose high implementation complexity on developers. To address these challenges, we design TokenRouter, an efficient and developer-friendly serving system for token-level routed LLM inference. TokenRouter follows the principle of request-centric programming, model-centric execution: developers describe routing logic from the perspective of a single request, while the runtime launches a subserver for each LLM and dispatches requests asynchronously. Each subserver employs a delayed-batching scheduler, whose optimal hyperparameters are derived from a mathematical throughput model of the system. Across diverse routing algorithms, workloads, and model pairs, TokenRouter achieves 2.01-64.15x higher decoding throughput than existing systems, substantially advancing the serving efficiency of token-level LLM routing. Our code is available at https://github.com/thu-nics/TokenRouter.

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.

Machine learning (ML) model serving has become a dominant consumer of GPU infrastructure, yet capacity planning in these systems remains largely ad hoc. Under-provisioning leads to service-level objective (SLO) violations and production incidents, while over-provisioning results in substantial resource waste. This paper presents \sys, an industrial load testing framework for ML serving systems that systematically estimates serving capacity through an adaptive, feedback-driven search strategy. The approach leverages real-time performance signals, incorporating dampening, spike tolerance, and convergence detection to efficiently identify maximum sustainable throughput under SLO constraints. We evaluate \sys through a longitudinal analysis of 14 industrial case studies spanning four ML architecture classes: recommendation, ranking, vision, and NLP. This study demonstrates that systematic load testing leads to substantial improvements in GPU resource efficiency and operational reliability. Prior to adopting \sys, a significant fraction of model launches were under-provisioned, resulting in recurring incidents; these issues were substantially reduced after deployment. Our results show that ML-specific design decisions are critical to accurate capacity estimation: workload calibration using recorded traffic reduces estimation error from approximately 30\% to 2--6\%, while proper warmup handling yields a 22.2\% improvement in accuracy. Further analysis reveals key factors influencing prediction error, including model size and co-location effects. This paper distills six lessons and derive architectural guidelines for ML load testing, offering actionable insights for building reliable and efficient ML serving systems.

Large language model (LLM)-based multi-agent systems (MAS) coordinate specialized agents to solve complex tasks, turning each user request into interdependent model and tool operations. Unlike independent requests, these operations become ready at different times and consume evolving context as agents coordinate and exchange results. This creates changing patterns of concurrency, computation, and memory demand that can expose different bottlenecks in LLM serving hardware. Yet benchmarking these effects requires capturing the collaboration rules that generate serving workloads, beyond the requests observed during execution. We present MAServeBench, a benchmark that treats multi-agent collaboration as a configurable dimension of serving workloads for LLM serving and hardware evaluation. Its composable stages capture how agents coordinate and exchange context in documented MAS workflows, enabling native executions to generate different workloads even when task inputs and tools remain unchanged. Hierarchical Semantic Traces preserve realized operations and dependencies for reproducible comparisons of legal release constraints at fixed work. Task-linked measurements connect these workloads to serving execution and GPU/NPU hardware behavior, revealing why serving efficiency does not always translate into timely task completion. The benchmark code is available at https://github.com/ShengxuanQiu/MAServeBench.

Retrieval-Augmented Generation (RAG) is a critical paradigm for building reliable, knowledge-intensive Large Language Model (LLM) applications. However, the multi-stage pipeline (retrieve, generate) and unique workload characteristics (e.g., knowledge dependency) of RAG systems pose significant challenges for serving performance optimization. Existing generic LLM inference traces fail to capture these RAG-specific dynamics, creating a significant performance gap between academic research and real-world deployment. To bridge this gap, this paper introduces RAGPulse, an open-source RAG workload trace dataset. This dataset was collected from an university-wide Q&A system serving that has served more than 40,000 students and faculties since April 2024. We detail RAGPulse's system architecture, its privacy-preserving hash-based data format, and provide an in-depth statistical analysis. Our analysis reveals that real-world RAG workloads exhibit significant temporal locality and a highly skewed hot document access pattern. RAGPulse provides a high-fidelity foundation for researchers to develop and validate novel optimization strategies for RAG systems, such as content-aware batching and retrieval caching, ultimately enhancing the efficiency and reliability of RAG services. The code is available at https://github.com/flashserve/RAGPulse.

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to Autoregressive Models (ARMs), utilizing parallel decoding to overcome sequential bottlenecks. However, existing research focuses primarily on kernel-level optimizations, lacking a holistic serving framework that addresses the unique memory dynamics of diffusion processes in production. We identify a critical "memory footprint crisis" specific to dLLMs, driven by monolithic logit tensors and the severe resource oscillation between compute-bound "Refresh" phases and bandwidth-bound "Reuse" phases. To bridge this gap, we present dLLM-Serve, an efficient dLLM serving system that co-optimizes memory footprint, computational scheduling, and generation quality. dLLM-Serve introduces Logit-Aware Activation Budgeting to decompose transient tensor peaks, a Phase-Multiplexed Scheduler to interleave heterogeneous request phases, and Head-Centric Sparse Attention to decouple logical sparsity from physical storage. We evaluate dLLM-Serve on diverse workloads (LiveBench, Burst, OSC) and GPUs (RTX 4090, L40S). Relative to the state-of-the-art baseline, dLLM-Serve improves throughput by 1.61times-1.81times on the consumer-grade RTX 4090 and 1.60times-1.74times on the server-grade NVIDIA L40S, while reducing tail latency by nearly 4times under heavy contention. dLLM-Serve establishes the first blueprint for scalable dLLM inference, converting theoretical algorithmic sparsity into tangible wall-clock acceleration across heterogeneous hardware.

Speculative decoding can significantly accelerate LLM serving, yet most deployments today disentangle speculator training from serving, treating speculator training as a standalone offline modeling problem. We show that this decoupled formulation introduces substantial deployment and adaptation lag: (1) high time-to-serve, since a speculator must be trained offline for a considerable period before deployment; (2) delayed utility feedback, since the true end-to-end decoding speedup is only known after training and cannot be inferred reliably from acceptance rate alone due to model-architecture and system-level overheads; and (3) domain-drift degradation, as the target model is repurposed to new domains and the speculator becomes stale and less effective. To address these issues, we present Aurora, a unified training-serving system that closes the loop by continuously learning a speculator directly from live inference traces. Aurora reframes online speculator learning as an asynchronous reinforcement-learning problem: accepted tokens provide positive feedback, while rejected speculator proposals provide implicit negative feedback that we exploit to improve sample efficiency. Our design integrates an SGLang-based inference server with an asynchronous training server, enabling hot-swapped speculator updates without service interruption. Crucially, Aurora supports day-0 deployment: a speculator can be served immediately and rapidly adapted to live traffic, improving system performance while providing immediate utility feedback. Across experiments, Aurora achieves a 1.5x day-0 speedup on recently released frontier models (e.g., MiniMax M2.1 229B and Qwen3-Coder-Next 80B). Aurora also adapts effectively to distribution shifts in user traffic, delivering an additional 1.25x speedup over a well-trained but static speculator on widely used models (e.g., Qwen3 and Llama3).

Large language models (LLMs), while driving a new wave of interactive AI applications across numerous domains, suffer from high inference costs and heavy cloud dependency. Motivated by the redundancy phenomenon in linguistics, we propose a progressive inference paradigm over cloud and edge, i.e., firstly generating the sketch of the answer by LLMs at cloud, and then conducting parallel extension to fill in details by small models (SLMs) at edge. Progressive inference offers potential benefits to improve throughput and reduce inference latency while facing key implementation challenges, including decreased response quality from SLMs, a tradeoff between the brevity and comprehensiveness of sketches, as well as increased latency caused by network transmission and edge inference. In this work, we propose and implement PICE, an LLM serving system with semantic-level cloud-edge collaboration, enhancing inference throughput and quality through dynamic inference task scheduling, ensemble learning, and parallel edge inference. Extensive testbed experiments illustrate that our approach achieves 1.5-2times throughput enhancement and up to 43% latency reduction, while also potentially enhancing the quality compared to SOTA systems.

Despite the rapid advancements of large language models (LLMs), LLM serving systems remain memory-intensive and costly. The key-value (KV) cache, which stores KV tensors during autoregressive decoding, is crucial for enabling low-latency, high-throughput LLM inference serving. In this survey, we focus on system-aware KV infrastructure for serving LLMs (abbreviated as sKis). We revisit recent work from a system behavior perspective, organizing existing efforts into three dimensions: execution and scheduling (temporal), placement and migration (spatial), and representation and retention (structural). Furthermore, we analyze cross-behavior co-design affinity and behavior-objective links, highlighting future opportunities. Our work systematizes a rapidly evolving area, providing a foundation for understanding and innovating KV cache designs in modern LLM serving infrastructure.

Large Language Models (LLMs) show great capabilities in a wide range of applications, but serving them efficiently becomes increasingly challenging as requests (prompts) become more complex. Context caching improves serving performance by reusing Key-Value (KV) vectors, the intermediate representations of tokens that are repeated across requests. However, existing context caching requires exact prefix matches across requests, limiting reuse cases in settings such as few-shot learning and retrieval-augmented generation, where immutable content (e.g., documents) remains unchanged across requests but is preceded by varying prefixes. Position-Independent Caching (PIC) addresses this issue by enabling modular reuse of the KV vectors regardless of prefixes. We formalize PIC and advance prior work by introducing EPIC, a serving system incorporating our new LegoLink algorithm, which mitigates the inappropriate "attention sink" effect at every document beginning, to maintain accuracy with minimal computation. Experiments show that EPIC achieves up to 8x improvements in Time-To-First-Token (TTFT) and 7x throughput gains over existing systems, with negligible or no accuracy loss.

The rapid evolution of large language models (LLMs) has unlocked their capabilities in advanced reasoning tasks like mathematical problem-solving, code generation, and legal analysis. Central to this progress are inference-time reasoning algorithms, which refine outputs by exploring multiple solution paths, at the cost of increasing compute demands and response latencies. Existing serving systems fail to adapt to the scaling behaviors of these algorithms or the varying difficulty of queries, leading to inefficient resource use and unmet latency targets. We present Dynasor, a system that optimizes inference-time compute for LLM reasoning queries. Unlike traditional engines, Dynasor tracks and schedules requests within reasoning queries and uses Certaindex, a proxy that measures statistical reasoning progress based on model certainty, to guide compute allocation dynamically. Dynasor co-adapts scheduling with reasoning progress: it allocates more compute to hard queries, reduces compute for simpler ones, and terminates unpromising queries early, balancing accuracy, latency, and cost. On diverse datasets and algorithms, Dynasor reduces compute by up to 50% in batch processing and sustaining 3.3x higher query rates or 4.7x tighter latency SLOs in online serving.

Large Language Model (LLM) inference in production must meet stringent service-level objectives for both time-to-first-token (TTFT) and time-between-token (TBT) while maximizing throughput under fixed compute, memory, and interconnect budgets. Modern serving systems adopt stall-free scheduling techniques such as chunked prefill, which splits long prompt processing along the token dimension and interleaves prefill with ongoing decode iterations. While effective at stabilizing TBT, chunked prefill incurs substantial overhead in Mixture-of-Experts (MoE) models: redundant expert weight loads increase memory traffic by up to 39% and inflate energy consumption. We propose layered prefill, a new scheduling paradigm that treats transformer layer groups as the primary scheduling unit. By vertically partitioning the model into contiguous layer groups and interleaving prefill and decode across the groups, layered prefill sustains stall-free decoding while eliminating chunk-induced MoE weight reloads. It reduces off-chip bandwidth demand, lowering TTFT by up to 70%, End-to-End latency by 41% and per-token energy by up to 22%. Evaluations show that layered prefill consistently improves the TTFT--TBT Pareto frontier over chunked prefill, reducing expert-load traffic and energy cost while maintaining stall-free decoding. Overall, shifting the scheduling axis from tokens to layers unlocks a new operating regime for high-efficiency, energy-aware LLM serving in co-located environments.

Any-to-any multimodal models that jointly handle text, images, video, and audio represent a significant advance in multimodal AI. However, their complex architectures (typically combining multiple autoregressive LLMs, diffusion transformers, and other specialized components) pose substantial challenges for efficient model serving. Existing serving systems are mainly tailored to a single paradigm, such as autoregressive LLMs for text generation or diffusion transformers for visual generation. They lack support for any-to-any pipelines that involve multiple interconnected model components. As a result, developers must manually handle cross-stage interactions, leading to huge performance degradation. We present vLLM-Omni, a fully disaggregated serving system for any-to-any models. vLLM-Omni features a novel stage abstraction that enables users to decompose complex any-to-any architectures into interconnected stages represented as a graph, and a disaggregated stage execution backend that optimizes resource utilization and throughput across stages. Each stage is independently served by an LLM or diffusion engine with per-stage request batching, flexible GPU allocation, and unified inter-stage connectors for data routing. Experimental results demonstrate that vLLM-Omni reduces job completion time (JCT) by up to 91.4% compared to baseline methods. The code is public available at https://github.com/vllm-project/vllm-omni.

LLM serving systems are provisioned for peak load to meet strict latency targets, leaving substantial GPU compute idle whenever traffic falls below peak. We present DeltaServe, a host-agnostic co-serving design that converts this idle inference capacity into LoRA fine-tuning throughput while preserving inference service-level objectives (SLOs). DeltaServe integrates with existing inference engines through a compact hook interface that requires only multi-LoRA batching support. It exploits the shared execution structure of inference prefill and LoRA fine-tuning forward passes, and uses an SLO-aware scheduler to admit and execute fine-tuning only when sufficient inference headroom is available. The scheduler is driven by a CUDA-graph-aware latency model calibrated offline and refined online. We integrate DeltaServe with vLLM, SGLang, and S-LoRA. On a production trace from Company X, DeltaServe on vLLM delivers 2.9x higher fine-tuning throughput than LLMStation at 100% inference SLO compliance, versus 85% for LLMStation. It also achieves 39% higher fine-tuning throughput than a baseline running vLLM+torchtune, using no additional hardware and maintaining full SLO compliance.

Streaming video generation is emerging as a new serving workload in which users interact with long-lived sessions that generate video progressively, chunk by chunk. Unlike offline video generation or typical LLM serving, streaming video generation must preserve session state across active and idle periods, repeatedly schedule ongoing sessions, and deliver each chunk under a tight latency target. This creates two key serving challenges in multi-user, multi-GPU environments: session duration heterogeneity, where long-running sessions make placement decisions suboptimal over time, and temporal user-demand heterogeneity, where the number of active sessions fluctuates sharply across bursts and idle periods. We present TurboServe, the first serving system designed specifically for streaming video generation workloads. TurboServe formulates serving as an online scheduling problem that jointly coordinates session placement and GPU provisioning. Its closed-loop scheduling algorithm combines a migration-aware placement controller, which rebalances sessions across GPUs to reduce the maximum per-chunk latency, with a load-driven autoscaling controller, which adapts the GPU budget to workload variation for improved cost efficiency. To support these decisions at runtime, TurboServe implements coalesced chunk processing for batching concurrent active sessions on the same GPU, GPU-CPU offloading for session suspension and resumption, and NCCL-based GPU-GPU migration for online rebalancing. We evaluate TurboServe on real-world production traces from Shengshu Technology across multiple model sizes and GPU clusters with up to 64 NVIDIA B300 GPUs. Compared with baseline serving configurations, TurboServe reduces worst-case per-chunk latency by 37.5% and total GPU operating cost by 37.2% on average. Our code is publicly available at https://github.com/shengshu-ai/TurboServe.

Inference serving for large language models (LLMs) is the key to unleashing their potential in people's daily lives. However, efficient LLM serving remains challenging today because the requests are inherently heterogeneous and unpredictable in terms of resource and latency requirements, as a result of the diverse applications and the dynamic execution nature of LLMs. Existing systems are fundamentally limited in handling these characteristics and cause problems such as severe queuing delays, poor tail latencies, and SLO violations. We introduce Llumnix, an LLM serving system that reacts to such heterogeneous and unpredictable requests by runtime rescheduling across multiple model instances. Similar to context switching across CPU cores in modern operating systems, Llumnix reschedules requests to improve load balancing and isolation, mitigate resource fragmentation, and differentiate request priorities and SLOs. Llumnix implements the rescheduling with an efficient and scalable live migration mechanism for requests and their in-memory states, and exploits it in a dynamic scheduling policy that unifies the multiple rescheduling scenarios elegantly. Our evaluations show that Llumnix improves tail latencies by an order of magnitude, accelerates high-priority requests by up to 1.5x, and delivers up to 36% cost savings while achieving similar tail latencies, compared against state-of-the-art LLM serving systems. Llumnix is publicly available at https://github.com/AlibabaPAI/llumnix.

Large language model (LLM) applications are evolving beyond simple chatbots into dynamic, general-purpose agentic programs, which scale LLM calls and output tokens to help AI agents reason, explore, and solve complex tasks. However, existing LLM serving systems ignore dependencies between programs and calls, missing significant opportunities for optimization. Our analysis reveals that programs submitted to LLM serving engines experience long cumulative wait times, primarily due to head-of-line blocking at both the individual LLM request and the program. To address this, we introduce Autellix, an LLM serving system that treats programs as first-class citizens to minimize their end-to-end latencies. Autellix intercepts LLM calls submitted by programs, enriching schedulers with program-level context. We propose two scheduling algorithms-for single-threaded and distributed programs-that preempt and prioritize LLM calls based on their programs' previously completed calls. Our evaluation demonstrates that across diverse LLMs and agentic workloads, Autellix improves throughput of programs by 4-15x at the same latency compared to state-of-the-art systems, such as vLLM.

Existing large language model (LLM) serving systems fall into two categories: 1) a unified system where prefill phase and decode phase are co-located on the same GPU, sharing the unified computational resource and storage, and 2) a disaggregated system where the two phases are disaggregated to different GPUs. The design of the disaggregated system addresses the latency interference and sophisticated scheduling issues in the unified system but leads to storage challenges including 1) replicated weights for both phases that prevent flexible deployment, 2) KV cache transfer overhead between the two phases, 3) storage imbalance that causes substantial wasted space of the GPU capacity, and 4) suboptimal resource adjustment arising from the difficulties in migrating KV cache. Such storage inefficiency delivers poor serving performance under high request rates. In this paper, we identify that the advantage of the disaggregated system lies in the disaggregated computation, i.e., partitioning the computational resource to enable the asynchronous computation of two phases. Thus, we propose a novel LLM serving system, semi-PD, characterized by disaggregated computation and unified storage. In semi-PD, we introduce a computation resource controller to achieve disaggregated computation at the streaming multi-processor (SM) level, and a unified memory manager to manage the asynchronous memory access from both phases. semi-PD has a low-overhead resource adjustment mechanism between the two phases, and a service-level objective (SLO) aware dynamic partitioning algorithm to optimize the SLO attainment. Compared to state-of-the-art systems, semi-PD maintains lower latency at higher request rates, reducing the average end-to-end latency per request by 1.27-2.58x on DeepSeek series models, and serves 1.55-1.72x more requests adhering to latency constraints on Llama series models.

Mixture-of-Experts (MoE) models challenge serving infrastructures with dynamic, sparse expert utilization, causing instability on conventional systems designed for dense architectures. We propose EaaS, a novel serving system to enable efficient, scalable, and robust MoE deployment. Our system disaggregates MoE modules into independent, stateless services. This design enables fine-grained resource scaling and provides inherent fault tolerance by decoupling compute units. The architecture is powered by a high-performance, CPU-free peer-to-peer communication library that ensures minimal overhead and high throughput. Experiments confirm EaaS's scalability and efficiency, achieving performance comparable to monolithic systems while providing robust fault tolerance and strong scalability. EaaS incurs less than a 2% throughput reduction under simulated hardware failures that would otherwise halt monolithic architectures. It further saves up to 37.5% of computing resources through dynamic fine-grained adaptation to serving traffic, demonstrating strong resilience for large-scale MoE deployment in production.

This paper presents Block, a distributed scheduling framework designed to optimize load balancing and auto-provisioning across instances in large language model serving frameworks by leveraging contextual information from incoming requests. Unlike popular model serving systems that rely on monolithic and heuristic task schedulers, Block operates as a fully distributed, stateless, and predictive scheduling system to achieve low overhead, reliability, and scalability. It leverages the deterministic and predictable characteristics of LLM inferences, such as host configurations, response lengths, and hardware performance, to make scheduling decisions based on accurately predicted metrics. Evaluation on a 12 GPUs cluster shows that Block significantly outperforms heuristic schedulers, boosting serving capacity by up to 16.7\% and reducing P99 tail latency by up to 49.5\%. These performance gains remain consistent across diverse models, workloads and configurations. Code and data are open-sourced.

The rapid advancement of Large Language Models (LLMs) has driven the need for more efficient serving strategies. In this context, efficiency refers to the proportion of requests that meet their Service Level Objectives (SLOs), particularly for Time To First Token (TTFT) and Time Between Tokens (TBT). However, existing systems often prioritize one metric at the cost of the other. We present Ascendra, an LLM serving system designed to meet both TTFT and TBT SLOs simultaneously. The core insight behind Ascendra is that a request's urgency evolves as it approaches its deadline. To leverage this, Ascendra partitions GPU resources into two types of instances: low-priority and high-priority. Low-priority instances maximize throughput by processing requests out of arrival order, but at the risk of request starvation. To address this, Ascendra employs a performance model to predict requests at risk of missing their SLOs and proactively offloads them to high-priority instances. High-priority instances are optimized for low-latency execution and handle urgent requests nearing their deadlines. This partitioned architecture enables Ascendra to effectively balance high throughput and low latency. Extensive evaluation shows that Ascendra improves system throughput by up to 1.7x compared to vLLM and Sarathi-Serve while meeting both TTFT and TBT SLOs.

The reasoning and agentic capabilities of large language models have expanded the range of applications they support, from short interactive exchanges to long, compute-heavy requests. LLM serving platforms today define response-latency service-level objectives, even though requests within the same service can differ by orders of magnitude in input length, generation length, execution cost, and the availability of reusable KV-cache state. As a result, requests governed by the same service level objective have different urgency: after accounting for the time required to execute them, some have substantial latency headroom while others have almost none. We define this headroom---the difference between a request's service level objective and its predicted remaining service time---as its per-request latency budget. We present Cascade, an LLM serving system that estimates and continuously updates this budget from request characteristics, KV-cache state, and current system load. Unlike prior SLO-aware schedulers that use deadlines to govern request ordering alone, Cascade uses a single per-request budget to jointly coordinate request scheduling and KV-cache management across the memory hierarchy. Its scheduler prioritizes requests with little remaining budget, while its memory manager uses the same budget to decide whether non-resident KV state should be restored or prefetched from a deeper tier, retained in HBM, or recomputed. By directing queueing and data-movement overhead toward requests that can absorb it, Cascade improves SLO-satisfied goodput while preserving fairness across heterogeneous request classes. On production traces across three large language models, Cascade improves goodput by up to2.4x and reduces SLO violations by 40% relative to the default vLLM first-come, first-served scheduler.

Large language models (LLMs) power a new generation of interactive AI applications exemplified by ChatGPT. The interactive nature of these applications demand low job completion time (JCT) for model inference. Existing LLM serving systems use run-to-completion processing for inference jobs, which suffers from head-of-line blocking and long JCT. We present FastServe, a distributed inference serving system for LLMs. FastServe exploits the autoregressive pattern of LLM inference to enable preemption at the granularity of each output token. FastServe uses preemptive scheduling to minimize JCT with a novel skip-join Multi-Level Feedback Queue scheduler. Based on the new semi information-agnostic setting of LLM inference, the scheduler leverages the input length information to assign an appropriate initial queue for each arrival job to join. The higher priority queues than the joined queue are skipped to reduce demotions. We design an efficient GPU memory management mechanism that proactively offloads and uploads intermediate states between GPU memory and host memory for LLM inference. We build a system prototype of FastServe based on NVIDIA FasterTransformer. Experimental results show that compared to the state-of-the-art solution Orca, FastServe improves the average and tail JCT by up to 5.1times and 6.4times, respectively.

Large Language Models (LLMs) have recently experienced great success, as evident in the widespread popularity of ChatGPT. Existing LLM serving systems are stateless across requests. Consequently, when LLMs are used in the common setting of multi-turn conversations, a growing log of the conversation history must be processed alongside any request by the serving system at each turn, resulting in repeated history processing. In this paper, we design Pensieve, a system optimized for multi-turn conversation LLM serving. Pensieve maintains the conversation state across requests by caching previously processed history to avoid duplicate processing. Pensieve's multi-tier caching strategy can utilize both GPU and CPU memory to efficiently store and retrieve cached data. Pensieve also generalizes the recent PagedAttention kernel to support attention between multiple input tokens with a GPU cache spread over non-contiguous memory. Our evaluation shows that Pensieve is able to achieve 1.51-1.95x throughput compared to vLLM and reduce latency by 60-75%.

DistServe improves the performance of large language models (LLMs) serving by disaggregating the prefill and decoding computation. Existing LLM serving systems colocate the two phases and batch the computation of prefill and decoding across all users and requests. We find that this strategy not only leads to strong prefill-decoding interferences but also couples the resource allocation and parallelism plans for both phases. LLM applications often emphasize individual latency for each phase: time to first token (TTFT) for the prefill phase and time per output token (TPOT) of each request for the decoding phase. In the presence of stringent latency requirements, existing systems have to prioritize one latency over the other, or over-provision compute resources to meet both. DistServe assigns prefill and decoding computation to different GPUs, hence eliminating prefill-decoding interferences. Given the application's TTFT and TPOT requirements, DistServe co-optimizes the resource allocation and parallelism strategy tailored for each phase. DistServe also places the two phases according to the serving cluster's bandwidth to minimize the communication caused by disaggregation. As a result, DistServe significantly improves LLM serving performance in terms of the maximum rate that can be served within both TTFT and TPOT constraints on each GPU. Our evaluations show that on various popular LLMs, applications, and latency requirements, DistServe can serve 4.48x more requests or 10.2x tighter SLO, compared to state-of-the-art systems, while staying within latency constraints for > 90% of requests.

Large Language Model (LLM) serving systems remain fundamentally fragile, where frequent hardware faults in hyperscale clusters trigger disproportionate service outages in the software stack. Current recovery mechanisms are prohibitively slow, often requiring up to 10 minutes to reinitialize resources and reload massive model weights. We introduce KevlarFlow, a fault tolerant serving architecture designed to bridge the gap between hardware unreliability and service availability. KevlarFlow leverages 1) decoupled model parallelism initialization, 2) dynamic traffic rerouting, and 3) background KV cache replication to maintain high throughput during partial failures. Our evaluation demonstrates that KevlarFlow reduces mean-time-to-recovery (MTTR) by 20x and, under failure conditions, improves average latency by 3.1x, 99th percentile (p99) latency by 2.8x, average time-to-first-token (TTFT) by 378.9x, and p99 TTFT by 574.6x with negligible runtime overhead in comparison to state-of-the-art LLM serving systems.

Mainstream LLM serving systems reuse prefix work mainly through paged or radix key-value (KV) caches. This is highly effective for high-throughput, high-concurrency serving, but it manages only one positional fragment of execution state: the KV cache. We study the opposite regime: low-latency, small-batch, on-device physical-AI serving, where interactive LLM agents, speech systems, and robot policies repeatedly branch, reset, interrupt, and re-enter under tight responsiveness budgets. We introduce execution-state capsules, a graph-bound checkpoint and restore mechanism for the complete restorable state at a committed boundary. FlashRT is a white-box, backend-facing kernel runtime whose evaluated NVIDIA CUDA backend runs captured graph plans over contiguous static buffers with no block-table indirection. Because the live state is a closed set of named buffers, a capsule can snapshot, restore, fork, or roll back the whole execution boundary, including KV, recurrent state, convolution state, MTP state, and metadata. This moves reuse from token-addressed KV fragments to graph-bound execution-state boundaries. On an RTX 5090, capsule restore is byte-exact at the stored-state level and token-identical under greedy decode. A KV-only ablation diverges, showing that recurrent state is load-bearing. GPU-resident snapshot and restore are sub-millisecond, and TTFT speedup over cold prefill grows from 3.9x at 2k tokens to 27x at 16k tokens. On Jetson AGX Thor and DGX Spark, the same correctness and structural properties hold. Capsules are not a replacement for high-throughput KV-cache serving; they define a complementary latency-first serving point for explicit execution-state reuse.

Multi-agent applications often execute complex tasks as multi-stage workflows, where each stage is an LLM call whose output becomes part of context for subsequent steps. Existing LLM serving systems largely assume homogeneous clusters with identical model replicas. This design overlooks the potential of heterogeneous deployments, where models of different sizes and capabilities enable finer trade-offs between latency and performance. However, heterogeneity introduces new challenges in scheduling across models with diverse throughput and performance. We present Chimera, a predictive scheduling system for multi-agent workflow serving on heterogeneous LLM clusters that jointly improves end-to-end latency and task performance. Chimera applies semantic routing to estimate per-model confidence scores for each request, predicts the total remaining output length of the workflow, and estimates per-model congestion using in-flight predicted token volumes for load balancing. We evaluate Chimera on representative agentic workflows for code generation and math reasoning using multiple heterogeneous LLM configurations. Across comparable settings, Chimera traces the best latency-performance frontier, reducing end-to-end latency by 1.2--2.4times and improving task performance by 8.0-9.5 percentage points on average over competitive baselines including vLLM.

Deploying multiple models within shared GPU clusters is a key strategy to improve resource efficiency in large language model (LLM) serving. Existing multi-LLM serving systems improve GPU utilization at the cost of degraded inference performance, particularly time-to-first-token (TTFT). We attribute this degradation to the lack of awareness regarding future workload characteristics. In contrast, recent analyses have shown the strong periodicity and long-term predictability of real-world LLM serving workloads. In this paper, we propose one-for-many GPU prewarming, which proactively loads parameters from multiple models onto GPUs based on workload forecasts. These prewarmed weights enable the system to promptly instantiate serving instances upon encountering request bursts. We design and implement WarmServe, a multi-LLM serving system incorporating three key techniques: (1) a model placement algorithm that optimizes prewarming decisions to minimize cross-model prewarming interference, (2) a KV cache reservation strategy that repurposes idle KV cache space on running GPUs for prewarming new models, and (3) an efficient GPU memory switching mechanism for tensor management. Evaluation on real-world datasets shows that WarmServe reduces tail TTFT by up to 50.8times compared to the state-of-the-art autoscaling-based system, while supporting up to 2.5times higher request throughput than the GPU-sharing system.

Many applications must provide low-latency LLM service to users or risk unacceptable user experience. However, over-provisioning resources to serve fluctuating request patterns is often prohibitively expensive. In this work, we present a best-effort serving system that employs deep reinforcement learning to adjust service quality based on the task distribution and system load. Our best-effort system can maintain availability with over 10x higher client request rates, serves above 96% of peak performance 4.1x more often, and serves above 98% of peak performance 2.3x more often than static serving on unpredictable workloads. Our learned router is robust to shifts in both the arrival and task distribution. Compared to static serving, learned best-effort serving allows for cost-efficient serving through increased hardware utility. Additionally, we argue that learned best-effort LLM serving is applicable in wide variety of settings and provides application developers great flexibility to meet their specific needs.

Serving numerous users and requests concurrently requires good fairness in Large Language Models (LLMs) serving system. This ensures that, at the same cost, the system can meet the Service Level Objectives (SLOs) of more users , such as time to first token (TTFT) and time between tokens (TBT), rather than allowing a few users to experience performance far exceeding the SLOs. To achieve better fairness, the preemption-based scheduling policy dynamically adjusts the priority of each request to maintain balance during runtime. However, existing systems tend to overly prioritize throughput, overlooking the overhead caused by preemption-induced context switching, which is crucial for maintaining fairness through priority adjustments. In this work, we identify three main challenges that result in this overhead. 1) Inadequate I/O utilization. 2) GPU idleness. 3) Unnecessary I/O transmission during multi-turn conversations. Our key insight is that the block-based KV cache memory policy in existing systems, while achieving near-zero memory waste, leads to discontinuity and insufficient granularity in the KV cache memory. To respond, we introduce FastSwitch, a fairness-aware serving system that not only aligns with existing KV cache memory allocation policy but also mitigates context switching overhead. Our evaluation shows that FastSwitch outperforms the state-of-the-art LLM serving system vLLM with speedups of 1.4-11.2x across different tail TTFT and TBT.

Multi-modal Large Language Models (MLLMs) serving systems commonly employ KV-cache compression to reduce memory footprint. However, existing compression methods introduce significant processing overhead and queuing delays, particularly in concurrent serving scenarios. We present FastCache, a novel serving framework that effectively addresses these challenges through two key innovations: (1) a dynamic batching strategy that optimizes request scheduling across prefill, compression, and decode stages, and (2) an efficient KV-cache memory pool mechanism that eliminates memory fragmentation while maintaining high GPU utilization. Our comprehensive experiments on the GQA and MileBench datasets demonstrate that FastCache achieves up to 19.3times reduction in Time-To-First-Token (TTFT) and 12.1times improvement in throughput compared to state-of-the-art baselines. The system maintains stable performance under high-concurrency scenarios (up to 40 req/s) while reducing average memory consumption by 20\%. These results establish FastCache as an efficient solution for real-world LLM serving systems with KV-cache compression.

Multimodal large language models (MLLMs) extend LLMs to handle images, videos, and audio by incorporating feature extractors and projection modules. However, these additional components -- combined with complex inference pipelines and heterogeneous workloads -- introduce significant inference overhead. Therefore, efficiently serving MLLMs remains a major challenge. Current tightly coupled serving architectures struggle to distinguish between mixed request types or adapt parallelism strategies to different inference stages, leading to increased time-to-first-token (TTFT) latency and poor resource utilization. To address this, we introduce Elastic Multimodal Parallelism (EMP), a new serving paradigm that elastically adapts to resource heterogeneity across request types and inference stages. Building upon EMP, we develop ElasticMM, an MLLM serving system that (1) separates requests into independent modality groups with dynamic resource allocation via a modality-aware load balancer; (2) decouples inference stages and enables parallelism adjustment and adaptive scaling via elastic partition scheduling; and (3) improves inference efficiency through unified multimodal prefix caching and non-blocking encoding. Experiments on diverse real-world datasets show that ElasticMM outperforms state-of-the-art (SOTA) serving systems, reducing TTFT by up to 4.2x and achieving 3.2-4.5x higher throughput while meeting service-level objectives (SLOs).

This paper documents our characterization study and practices for serving text-to-image requests with stable diffusion models in production. We first comprehensively analyze inference request traces for commercial text-to-image applications. It commences with our observation that add-on modules, i.e., ControlNets and LoRAs, that augment the base stable diffusion models, are ubiquitous in generating images for commercial applications. Despite their efficacy, these add-on modules incur high loading overhead, prolong the serving latency, and swallow up expensive GPU resources. Driven by our characterization study, we present SwiftDiffusion, a system that efficiently generates high-quality images using stable diffusion models and add-on modules. To achieve this, SwiftDiffusion reconstructs the existing text-to-image serving workflow by identifying the opportunities for parallel computation and distributing ControlNet computations across multiple GPUs. Further, SwiftDiffusion thoroughly analyzes the dynamics of image generation and develops techniques to eliminate the overhead associated with LoRA loading and patching while preserving the image quality. Last, SwiftDiffusion proposes specialized optimizations in the backbone architecture of the stable diffusion models, which are also compatible with the efficient serving of add-on modules. Compared to state-of-the-art text-to-image serving systems, SwiftDiffusion reduces serving latency by up to 5x and improves serving throughput by up to 2x without compromising image quality.

Efficiently serving Large Language Models (LLMs) requires selecting an optimal parallel execution plan, balancing computation, memory, and communication overhead. However, determining the best strategy is challenging due to varying parallelism techniques (data, pipeline, tensor) and workload characteristics (e.g., compute-intensive tasks with long prompts vs. memory-intensive tasks with long generation). We propose APEX, an LLM serving system simulator that efficiently identifies optimal parallel execution plans by considering key factors of LLM serving systems, such as memory usage, batching behavior, etc. APEX performs dynamism-aware simulation to model iteration-level batching, and leverages LLMs' repetitive structure to reduce design space, scaling efficiently to trillion-scale models. APEX abstracts the key components of LLM serving systems, including the model, batching module, quantization formats, and device clusters, enabling the simulator to be general and extensible. Simulating on a CPU, APEX evaluates execution plans for various device clusters, covering diverse LLMs and workloads. APEX finds plans up to 3.37x faster than heuristics, and also plans that reduce energy consumption by up to 45% compared to latency-optimal plans. APEX performs comprehensive evaluations, reporting key system metrics like time per output token and time to first token, which can help service providers meet SLOs. APEX identifies an optimal plan within 15 minutes on a CPU, making it 71x faster and 1234x more cost-effective than cloud-based GPU deployment. APEX can be accessed at https://github.com/microsoft/apex_plus

Adapting large language models (LLMs) via reinforcement learning (RL) is often bottlenecked by the generation stage, which can consume over 75\% of the training time. Speculative decoding (SD) accelerates autoregressive generation in serving systems, but its behavior under RL training remains largely unexplored. We identify three critical gaps that hinder the naive integration of SD into RL systems: diminishing speedups at large batch sizes, drafter staleness under continual actor updates, and drafter-induced policy degradation. To address these gaps, we present ReSpec, a system that adapts SD to RL through three complementary mechanisms: dynamically tuning SD configurations, evolving the drafter via knowledge distillation, and weighting updates by rollout rewards. On Qwen models (3B--14B), ReSpec achieves up to 4.5x speedup while preserving reward convergence and training stability, providing a practical solution for efficient RL-based LLM adaptation.

Modern applications increasingly rely on inference serving systems to provide low-latency insights with a diverse set of machine learning models. Existing systems often utilize resource elasticity to scale with demand. However, many applications cannot rely on hardware scaling when deployed at the edge or other resource-constrained environments. In this work, we propose a model selection and scheduling algorithm that implements accuracy scaling to increase efficiency for these more constrained deployments. We show that existing schedulers that make decisions using profiled model accuracy are biased toward the label distribution present in the test dataset. To address this problem, we propose using ML models -- which we call SneakPeek models -- to dynamically adjust estimates of model accuracy, based on the underlying data. Furthermore, we greedily incorporate inference batching into scheduling decisions to improve throughput and avoid the overhead of swapping models in and out of GPU memory. Our approach employs a new notion of request priority, which navigates the trade-off between attaining high accuracy and satisfying deadlines. Using data and models from three real-world applications, we show that our proposed approaches result in higher-utility schedules and higher accuracy inferences in these hardware-constrained environments.

Linear attention has recently gained significant attention for long-context inference due to its constant decoding cost with respect to context length. However, existing serving systems typically serve linear attention by recurrently computing and updating a large linear attention state in every decoding step. Since the state is much larger than the per-token key and value, recurrent decoding incurs substantial memory access and becomes inefficient for serving linear attention. In this paper, we propose KVBuffer, an IO-aware serving mechanism for linear attention. By buffering recent keys and values, KVBuffer enables serving systems to compute linear attention outputs in more flexible and memory-efficient ways. For decoding, KVBuffer enables chunkwise computation, which reduces average memory access and decoding latency by deferring state updates and applying them in batch. For speculative decoding, KVBuffer verifies draft tokens in parallel and avoids storing temporary states. For short contexts, KVBuffer computes attention outputs directly from buffered keys and values, without creating or updating the linear attention state. We implement KVBuffer in SGLang for Qwen3-Next. Our evaluations show that KVBuffer can reduce linear attention decoding latency by up to 45.17% and increase the maximum number of serving requests by 5x for speculative decoding when verifying four draft tokens.

Agentic workloads are a major source of LLM inference demand. Existing prefill--decode (PD) disaggregated serving systems offer limited flexibility for runtime adaptation of compute allocation and KV cache management, and rely on coarse signals that only partly capture the diverse and dynamic agent workload. These limitations lead to load imbalance between prefill and decode nodes and eviction of KV caches that agents will reuse. We present Evolving Infra, an agent-adaptive serving framework that adapts compute allocation to agent workloads and KV cache management to agent context management at runtime. We decouple compute allocation from key--value (KV) cache management, allowing nodes to switch efficiently between prefill and decode. Building on this design, an online planner matches the PD split to workload composition, while an agent-aware distributed KV manager guides cache eviction and transfer with signals from agent context management. Across coding, math, and computer-use tasks with GLM-5.2 and Kimi K2.6 on up to 256 GB300 GPUs, Evolving Infra reduces mean end-to-end request latency and P95 TTFT by up to 4.1x and 14x over Dynamo, NVIDIA's production framework.

The high computational and memory requirements of generative large language models (LLMs) make it challenging to serve them quickly and cheaply. This paper introduces SpecInfer, an LLM serving system that accelerates generative LLM inference with speculative inference and token tree verification. A key insight behind SpecInfer is to combine various collectively boost-tuned small language models to jointly predict the LLM's outputs; the predictions are organized as a token tree, whose nodes each represent a candidate token sequence. The correctness of all candidate token sequences represented by a token tree is verified by the LLM in parallel using a novel tree-based parallel decoding mechanism. SpecInfer uses an LLM as a token tree verifier instead of an incremental decoder, which significantly reduces the end-to-end latency and computational requirement for serving generative LLMs while provably preserving model quality.

The growing demand for Large Language Models (LLMs) across diverse applications has prompted a paradigm shift in the design of deep learning serving systems. Deploying LLMs, especially in multi-tenant environments, presents considerable challenges due to their high computational and memory demands. We present BlockLLM, a serving system that exploits the potential of sharing components among fine-tuned LLM models to offer an efficient and flexible solution for LLM workloads. BlockLLM partitions the models into finer-grained blocks to enable the reuse of model components and independent provisioning to improve the computation efficiency. BlockLLM consists of an offline block zoo, for storing the blocks, and an online system to serve the requests through chains of blocks. It offers multi-fold flexibility: (1) Adaptive assembly of block chains on-the-fly is achieved with the help of equivalence evaluation among blocks in the zoo. (2) We enable per-block batch size and configure best-effort KV cache coordination at individual block level. (3) We adopt speculative execution and locality-aware block placement to mitigate the communication costs from dynamic block resource allocation. Our evaluation demonstrates that BlockLLM reduces memory and storage footprints and improves computation efficiency, outperforming existing serving approach in 95\%ile latency and GPU utilization by 33.5\% and 20.1\%, respectively.

The complexity of large language model (LLM) serving workloads has substantially increased due to the integration with external tool invocations, such as ChatGPT plugins. In this paper, we identify a new opportunity for efficient LLM serving for requests that trigger tools: tool partial execution alongside LLM decoding. To this end, we design Conveyor, an efficient LLM serving system optimized for handling requests involving external tools. We introduce a novel interface for tool developers to expose partial execution opportunities to the LLM serving system and a request scheduler that facilitates partial tool execution. Our results demonstrate that tool partial execution can improve request completion latency by up to 38.8%.

Frontier open-weight models are increasingly available, but serving them still largely assumes datacenter infrastructure. We present FreeToken, an edge-native MoE serving system that treats a personal machine not as a small GPU, but as a unified, elastic inference platform. FreeToken co-designs the full serving stack, including model layout and loading, expert residency, CPU--GPU execution, agentic state reuse, and runtime memory management, around two realities of local AI: agent workloads continuously change their execution pattern, and edge hardware exposes heterogeneous resources whose balance differs from machine to machine. Rather than committing to a fixed offloading strategy, FreeToken continuously maps computation and model state onto the resources actually available. FreeToken supports more than 20 MoE models and real coding and tool-using agents across hardware ranging from an 8GB laptop GPU to a single workstation GPU. More importantly, it changes what these machines can practically serve, from a 35B model on a laptop to a 284B model on a gaming desktop and the 753B GLM-5.2 on a single workstation GPU. FreeToken turns open weights into deployable local software, making the machines users already own a practical platform for frontier-scale intelligence. We release the system at flashml.ai.

Reducing the inference latency of large language models (LLMs) is crucial, and speculative decoding (SD) stands out as one of the most effective techniques. Rather than letting the LLM generate all tokens directly, speculative decoding employs effective proxies to predict potential outputs, which are then verified by the LLM without compromising the generation quality. Yet, deploying SD in real online LLM serving systems (with continuous batching) does not always yield improvement -- under higher request rates or low speculation accuracy, it paradoxically increases latency. Furthermore, there is no best speculation length work for all workloads under different system loads. Based on the observations, we develop a dynamic framework SmartSpec. SmartSpec dynamically determines the best speculation length for each request (from 0, i.e., no speculation, to many tokens) -- hence the associated speculative execution costs -- based on a new metric called goodput, which characterizes the current observed load of the entire system and the speculation accuracy. We show that SmartSpec consistently reduces average request latency by up to 3.2x compared to non-speculative decoding baselines across different sizes of target models, draft models, request rates, and datasets. Moreover, SmartSpec can be applied to different styles of speculative decoding, including traditional, model-based approaches as well as model-free methods like prompt lookup and tree-style decoding.

Expert-Specialized Fine-Tuning (ESFT) adapts Mixture-of-Experts (MoE) large language models to enhance their task-specific performance by selectively tuning the top-activated experts for the task. Serving these fine-tuned models at scale is challenging: deploying merged models in isolation is prohibitively resource-hungry, while existing multi-adapter serving systems with LoRA-style additive updates are incompatible with ESFT's expert-oriented paradigm. We present ExpertWeave, a system that serves multiple ESFT adapters concurrently over a single shared MoE base model, drastically reducing the memory footprint and improving resource utilization. To seamlessly integrate into existing inference pipelines for MoE models with non-intrusive modifications and minimal latency overhead, ExpertWeave introduces a virtual-memory-assisted expert weight manager that co-locates base-model and adapter experts without incurring memory overhead from fragmentation, and a fused kernel for batched rerouting to enable lightweight redirection of tokens to the appropriate experts at runtime. Our evaluations show that ExpertWeave can simultaneously serve multiple adapters of a 16B MoE model on a single accelerator where the baseline runs out of memory, or provides up to 94x more KV cache capacity and achieves up to 18% higher throughput while using comparable resources, all without compromising model accuracy. ExpertWeave maintains low overhead even when scaling to 20 adapters, with a 4-11% latency increase compared with serving the base model alone. Source code will be released soon.

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.

Fine-tuning large language models (LLMs) for downstream tasks can greatly improve model quality, however serving many different fine-tuned LLMs concurrently for users in multi-tenant environments is challenging. Dedicating GPU memory for each model is prohibitively expensive and naively swapping large model weights in and out of GPU memory is slow. Our key insight is that fine-tuned models can be quickly swapped in and out of GPU memory by extracting and compressing the delta between each model and its pre-trained base model. We propose DeltaZip, an LLM serving system that efficiently serves multiple full-parameter fine-tuned models concurrently by aggressively compressing model deltas by a factor of 6times to 8times while maintaining high model quality. DeltaZip increases serving throughput by 1.5times to 3times and improves SLO attainment compared to a vanilla HuggingFace serving system.

Large language models (LLMs) have facilitated a wide range of applications with distinct service-level objectives (SLOs), from latency-sensitive online tasks like interactive chatbots to throughput-oriented offline workloads like document summarization. The existing deployment model, which dedicates machines to each workload, simplifies SLO management but often leads to poor resource utilization. This paper introduces HyGen, an interference-aware LLM serving system that enables efficient co-location of online and offline workloads while preserving latency requirements. HyGen incorporates two key innovations: (1) performance control mechanisms, including a latency predictor to estimate batch execution time and an SLO-aware profiler to quantify latency interference, and (2) SLO-aware offline scheduling policies that maximize serving throughput and prevent starvation, without compromising online serving latency. Our evaluation on production workloads shows that HyGen achieves up to 3.87x overall throughput and 5.84x offline throughput gains over online and hybrid serving baselines, respectively, while strictly satisfying latency SLOs.

The integration of Large Language Models (LLMs) into applications ranging from interactive chatbots to multi-agent systems has introduced a wide spectrum of service-level objectives (SLOs) for responsiveness. These include latency-sensitive requests emphasizing per-token latency in streaming chat, deadline-sensitive requests requiring rapid full responses to trigger external tools, and compound requests with evolving dependencies across multiple LLM calls. Despite-or perhaps, because of-this workload diversity and unpredictable request information (e.g., response lengths and dependencies), existing request schedulers have focused on aggregate performance, unable to ensure application-level SLO needs. This paper presents JITServe, the first SLO-aware LLM serving system designed to maximize service goodput (e.g., the number of tokens meeting request SLOs) across diverse workloads. JITServe novelly schedules requests using imprecise request information and gradually relaxes this conservatism by refining request information estimates as generation progresses. It applies a grouped margin goodput maximization algorithm to allocate just enough serving bandwidth to satisfy each request's SLO just-in-time (JIT), maximizing residual capacity for others, while deciding the composition of requests in a batch to maximize efficiency and goodput with provable guarantees. Our evaluation across diverse realistic workloads, including chat, deep research, and agentic pipelines, shows that JITServe improves service goodput by 1.4x-6.3x, alternatively achieving 28.5%-83.2% resource savings, compared to state-of-the-art designs.

Coding agents powered by large language models (LLMs) repeatedly alternate between model inference and tool calls, creating long-lived sessions with reusable key-value (KV) states and asynchronous request resumptions. Logical readiness, however, does not ensure efficient admission in a shared serving system. Through direct trace analysis and trace-driven replay, we identify two mismatches: reusable KV states reside across storage tiers and incur unequal computational costs for state preparation, while requests with heterogeneous context lengths can decode inefficiently together. Our central insight is that exploiting admission flexibility can improve serving performance while preserving request progress. We present Coda, a coding-agent serving system that realizes this insight through a readiness-informed admission layer incorporating two mechanisms. Tiered-Aging state admission exploits bounded flexibility in admission order to improve admission efficiency and preserve request progress. Compatibility-Aware execution admission exploits flexibility in attention grouping within each model iteration to reduce mixed-context interference and improve shared decoding efficiency. For multi-worker configurations, Coda introduces a separate routing layer that considers KV-state residency, worker load, and request-to-worker context-length compatibility to guide efficient request placement. We evaluate Coda across different models and workloads against state-of-the-art coding-agent serving systems and vLLM. Across the single-worker and multi-worker experiments, Coda improves output-token and SLO-compliant throughput by 20.3% and 70.5% on average, with peak gains of 29.3% and 140.2%.

The growing demand for large language models (LLMs) requires serving systems to handle many concurrent requests with diverse service level objectives (SLOs). This exacerbates head-of-line (HoL) blocking during the compute-intensive prefill phase, where long-running requests monopolize resources and delay higher-priority ones, leading to widespread time-to-first-token (TTFT) SLO violations. While chunked prefill enables interruptibility, it introduces an inherent trade-off between responsiveness and throughput: reducing chunk size improves response latency but degrades computational efficiency, whereas increasing chunk size maximizes throughput but exacerbates blocking. This necessitates an adaptive preemption mechanism. However, dynamically balancing execution granularity against scheduling overheads remains a key challenge. In this paper, we propose FlowPrefill, a TTFT-goodput-optimized serving system that resolves this conflict by decoupling preemption granularity from scheduling frequency. To achieve adaptive prefill scheduling, FlowPrefill introduces two key innovations: 1) Operator-Level Preemption, which leverages operator boundaries to enable fine-grained execution interruption without the efficiency loss associated with fixed small chunking; and 2) Event-Driven Scheduling, which triggers scheduling decisions only upon request arrival or completion events, thereby supporting efficient preemption responsiveness while minimizing control-plane overhead. Evaluation on real-world production traces shows that FlowPrefill improves maximum goodput by up to 5.6times compared to state-of-the-art systems while satisfying heterogeneous SLOs.

Efficient scheduling of LLM inference tasks is essential for achieving low latency and high throughput, particularly with the growing use of reasoning-capable LLMs. Traditional strategies like First-Come-First-Serve (FCFS) often suffer from Head-of-Line (HOL) blocking, where long-running tasks delay shorter ones queued behind them. In this paper, we introduce PARS, a prompt-aware LLM task scheduler that improves serving efficiency by approximating shortest-job-first (SJF) scheduling through pairwise ranking with margin ranking loss. PARS focuses on impactful scheduling decisions and is seamlessly integrated into the state-of-the-art LLM serving system vLLM. It effectively predicts response-length-based task ordering, reducing latency with minimal overhead. Extensive experiments across multiple LLMs and real-world inference datasets show that PARS significantly improves performance, including for reasoning workloads. Furthermore, our cross-model evaluations demonstrate that the design generalizes well, enabling effective scheduling even when predictors are trained on different LLMs.

Large language model (LLM) serving infrastructures are undergoing a shift toward heterogeneity and disaggregation. Modern deployments increasingly integrate diverse accelerators and near-memory processing technologies, introducing significant hardware heterogeneity, while system software increasingly separates computation, memory, and model components across distributed resources to improve scalability and efficiency. As a result, LLM serving performance is no longer determined by hardware or software choices in isolation, but by their runtime interaction through scheduling, data movement, and interconnect behavior. However, understanding these interactions remains challenging, as existing simulators lack the ability to jointly model heterogeneous hardware and disaggregated serving techniques within a unified, runtime-driven framework. This paper presents LLMServingSim 2.0, a unified system-level simulator designed to make runtime-driven hardware-software interactions in heterogeneous and disaggregated LLM serving infrastructures explicit and analyzable. LLMServingSim 2.0 embeds serving decisions and hardware behavior into a single runtime loop, enabling interaction-aware modeling of batching, routing, offloading, memory, and power. The simulator supports extensible integration of emerging accelerators and memory systems through profile-based modeling, while capturing dynamic serving behavior and system-level effects. We validate LLMServingSim 2.0 against real deployments, showing that it reproduces key performance, memory, and power metrics with an average error of 0.95%, while maintaining simulation times of around 10 minutes even for complex configurations. These results demonstrate that LLMServingSim 2.0 provides a practical bridge between hardware innovation and serving-system design, enabling systematic exploration and co-design for next-generation LLM serving infrastructures.

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.

Low-rank adaptation (LoRA) has become an important and popular method to adapt pre-trained models to specific domains. We present Punica, a system to serve multiple LoRA models in a shared GPU cluster. Punica contains a new CUDA kernel design that allows batching of GPU operations for different LoRA models. This allows a GPU to hold only a single copy of the underlying pre-trained model when serving multiple, different LoRA models, significantly enhancing GPU efficiency in terms of both memory and computation. Our scheduler consolidates multi-tenant LoRA serving workloads in a shared GPU cluster. With a fixed-sized GPU cluster, our evaluations show that Punica achieves 12x higher throughput in serving multiple LoRA models compared to state-of-the-art LLM serving systems while only adding 2ms latency per token. Punica is open source at https://github.com/punica-ai/punica .

The increasing usage of Large Language Models (LLMs) has resulted in a surging demand for planet-scale serving systems, where tens of thousands of GPUs continuously serve hundreds of millions of users. Consequently, throughput (under reasonable latency constraints) has emerged as a key metric that determines serving systems' performance. To boost throughput, various methods of inter-device parallelism (e.g., data, tensor, pipeline) have been explored. However, existing methods do not consider overlapping the utilization of different resources within a single device, leading to underutilization and sub-optimal performance. We propose NanoFlow, a novel serving framework that exploits intra-device parallelism, which overlaps the usage of resources including compute, memory, and network within a single device through operation co-scheduling. To exploit intra-device parallelism, NanoFlow introduces two key innovations: First, NanoFlow splits requests into nano-batches at the granularity of operations, which breaks the dependency of sequential operations in LLM inference and enables overlapping; then, to get benefit from overlapping, NanoFlow uses an operation-level pipeline with execution unit scheduling, which partitions the device's functional units and simultaneously executes different operations in each unit. NanoFlow automates the pipeline setup using a parameter search algorithm, which enables easily porting NanoFlow to different models. We implement NanoFlow on NVIDIA GPUs and evaluate end-to-end serving throughput on several popular models such as LLaMA-2-70B, Mixtral 8x7B, LLaMA-3-8B, etc.. With practical workloads, NanoFlow provides 1.91x throughput boost compared to state-of-the-art serving systems achieving 59% to 72% of optimal throughput across ported models.

Large Language Models (LLMs) with Mixture of Experts (MoE) architectures achieve remarkable performance improvements, but their random expert selection mechanism introduces significant data movement overhead that becomes the dominant bottleneck in multi-unit serving systems. To forecast the patterns underlying this data movement, we conduct comprehensive data-movement-centric profiling across three state-of-the-art large-scale MoE models (200B- 671B) using over 24,000 requests spanning diverse workloads. With the resulting 150GB+ trace files, we perform systematic analysis from both temporal and spatial perspectives and distill six key insights to guide the design of diverse future serving systems. Taking wafer-scale GPUs as a case study, we demonstrate that minor architectural modifications leveraging our insights achieve substantial performance gains, delivering 6.3X and 4.0X average speedups on DeepSeek V3 and Qwen3, respectively. Our work provides the first comprehensive data-centric analysis of MoE models at scale. Our profiling traces and analysis results are publicly available at {https://huggingface.co/datasets/core12345/MoE_expert_selection_trace. We will also release our simulation framework shortly to facilitate future research in this area.

Large Language Model (LLM) serving has become a critical cloud workload, and realistic traces are essential for motivating and benchmarking serving systems. However, existing LLM serving workload studies remain limited in scale and scope. They often observe short time periods and provide limited visibility into how users interact with models in production. As a result, they do not fully capture how LLM serving workloads evolve over time or how user-model interactions shape production traffic. In this work, we further the understanding of real-world LLM serving workloads through both a global characterization and a longitudinal study of a one-year production trace from CompanyX. Unlike prior studies, our trace captures full production behavior across many models and users, including both popular and long-tail models. We analyze the workload from aggregate, temporal, model-level, and user-level perspectives, revealing workload evolution and user-model structure that are typically hidden behind aggregate views. To support future research, we publicly release the full one-year trace, enabling downstream studies of production behavior without relying on sampled or synthetically generated workloads. The trace is available at https://github.com/HarvardMadSys/chutes_workload.

High throughput serving of large language models (LLMs) requires batching sufficiently many requests at a time. However, existing systems struggle because the key-value cache (KV cache) memory for each request is huge and grows and shrinks dynamically. When managed inefficiently, this memory can be significantly wasted by fragmentation and redundant duplication, limiting the batch size. To address this problem, we propose PagedAttention, an attention algorithm inspired by the classical virtual memory and paging techniques in operating systems. On top of it, we build vLLM, an LLM serving system that achieves (1) near-zero waste in KV cache memory and (2) flexible sharing of KV cache within and across requests to further reduce memory usage. Our evaluations show that vLLM improves the throughput of popular LLMs by 2-4times with the same level of latency compared to the state-of-the-art systems, such as FasterTransformer and Orca. The improvement is more pronounced with longer sequences, larger models, and more complex decoding algorithms. vLLM's source code is publicly available at https://github.com/vllm-project/vllm

This paper presents MoE-Infinity, a cost-efficient mixture-of-expert (MoE) serving system that realizes activation-aware expert offloading. MoE-Infinity features sequence-level expert activation tracing, a new approach adept at identifying sparse activations and capturing the temporal locality of MoE inference. By analyzing these traces, MoE-Infinity performs novel activation-aware expert prefetching and caching, substantially reducing the latency overheads usually associated with offloading experts for improved cost performance. Extensive experiments in a cluster show that MoE-Infinity outperforms numerous existing systems and approaches, reducing latency by 4 - 20X and decreasing deployment costs by over 8X for various MoEs. MoE-Infinity's source code is publicly available at https://github.com/TorchMoE/MoE-Infinity

Large language model (LLM) inference workload dominates a wide variety of modern AI applications, ranging from multi-turn conversation to document analysis. Balancing fairness and efficiency is critical for managing diverse client workloads with varying prefix patterns. Unfortunately, existing fair scheduling algorithms for LLM serving, such as Virtual Token Counter (VTC), fail to take prefix locality into consideration and thus suffer from poor performance. On the other hand, locality-aware scheduling algorithms in existing LLM serving frameworks tend to maximize the prefix cache hit rate without considering fair sharing among clients. This paper introduces the first locality-aware fair scheduling algorithm, Deficit Longest Prefix Match (DLPM), which can maintain a high degree of prefix locality with a fairness guarantee. We also introduce a novel algorithm, Double Deficit LPM (D^2LPM), extending DLPM for the distributed setup that can find a balance point among fairness, locality, and load-balancing. Our extensive evaluation demonstrates the superior performance of DLPM and D^2LPM in ensuring fairness while maintaining high throughput (up to 2.87times higher than VTC) and low per-client (up to 7.18times lower than state-of-the-art distributed LLM serving system) latency.

Coding agents are rapidly becoming a major application of agentic LLMs, but serving them efficiently remains challenging. Progress on this challenge requires understanding real workload patterns, yet the data needed for such analysis is largely absent. Existing public traces and benchmarks do not capture real, day-to-day coding-agent usage across multiple agents and model families for serving-system analysis. To help fill this gap, we collect and release a trace of roughly 4,300 coding-agent sessions, containing about 350,000 LLM steps and 430,000 tool calls from our own day-to-day use of Claude Code and Codex. Our analysis shows that coding-agent workloads feature long autonomous loops, long contexts with short outputs, diverse and heavily-tailed tool calls, and high but imperfect prefix cache hit rates. These findings point to concrete opportunities for optimizing serving, including lower-overhead tool calling, append-length-aware prefill, semantic-aware tool-latency prediction, and improved KV-cache management around human-paced gaps. We release the dataset, trace collection pipeline, and analysis code at https://github.com/uw-syfi/TraceLab.git the project website is https://tracelab.cs.washington.edu.

Deploying LLMs efficiently requires testing hundreds of serving configurations, but evaluating each one on a GPU cluster takes hours and costs thousands of dollars. Discrete-event simulators are faster and cheaper, but they require re-implementing the serving system's control logic -- a burden that compounds as frameworks evolve. We present Revati, a time-warp emulator that enables performance modeling by directly executing real serving system code at simulation-like speed. The system intercepts CUDA API calls to virtualize device management, allowing serving frameworks to run without physical GPUs. Instead of executing GPU kernels, it performs time jumps -- fast-forwarding virtual time by predicted kernel durations. We propose a coordination protocol that synchronizes these jumps across distributed processes while preserving causality. On vLLM and SGLang, Revati achieves less than 5% prediction error across multiple models and parallelism configurations, while running 5-17x faster than real GPU execution.

Large language models (LLMs) have surged in popularity and are extensively used in commercial applications, where the efficiency of model serving is crucial for the user experience. Most current research focuses on optimizing individual sub-procedures, e.g. local inference and communication, however, there is no comprehensive framework that provides a holistic system view for optimizing LLM serving in an end-to-end manner. In this work, we conduct a detailed analysis to identify major bottlenecks that impact end-to-end latency in LLM serving systems. Our analysis reveals that a comprehensive LLM serving endpoint must address a series of efficiency bottlenecks that extend beyond LLM inference. We then propose ScaleLLM, an optimized system for resource-efficient LLM serving. Our extensive experiments reveal that with 64 concurrent requests, ScaleLLM achieves a 4.3x speed up over vLLM and outperforms state-of-the-arts with 1.5x higher throughput.

Large Language Models (LLMs) represent a revolutionary advancement in the contemporary landscape of artificial general intelligence (AGI). As exemplified by ChatGPT, LLM-based applications necessitate minimal response latency and maximal throughput for inference serving. However, due to the unpredictability of LLM execution, the first-come-first-serve (FCFS) scheduling policy employed by current LLM serving systems suffers from head-of-line (HoL) blocking issues and long job response times. In this paper, we propose a new efficient LLM inference serving framework, named ALISE. The key design paradigm of ALISE is to leverage a novel speculative scheduler by estimating the execution time for each job and exploiting such prior knowledge to assign appropriate job priority orders, thus minimizing potential queuing delays for heterogeneous workloads. Furthermore, to mitigate the memory overhead of the intermediate key-value (KV) cache, we employ a priority-based adaptive memory management protocol and quantization-based compression techniques. Evaluations demonstrate that in comparison to the state-of-the-art solution vLLM, ALISE improves the throughput of inference serving by up to 1.8x and 2.1x under the same latency constraint on the Alpaca and ShareGPT datasets, respectively.

The increasing demand for large language model (LLM) serving has necessitated significant advancements in the optimization and profiling of LLM inference systems. As these models become integral to a wide range of applications, the need for efficient and scalable serving solutions has grown exponentially. This work introduces TokenSim, a comprehensive hardware and software exploration system designed specifically for LLM inference. TokenSim is characterized by its support for extensible system optimizations including scheduling and memory management. We validate the results with systems running with realworld datasets, achieving an error rate of less than 1%. Furthermore, TokenSim facilitates various insightful explorations into the performance and optimization of LLM serving systems.

Large multimodal models (LMMs) demonstrate impressive capabilities in understanding images, videos, and audio beyond text. However, efficiently serving LMMs in production environments poses significant challenges due to their complex architectures and heterogeneous characteristics across their multi-stage inference pipelines. We present the first comprehensive systems analysis of two prominent LMM architectures, decoder-only and cross-attention, across six representative open-source models, revealing key systems design implications. We also present an in-depth analysis of production LMM inference traces, uncovering unique workload characteristics, including variable, heavy-tailed request distributions and bursty traffic patterns. Based on these insights, we propose ModServe, a modular LMM serving system that decouples stages for independent optimization and adaptive scaling. ModServe dynamically reconfigures stages and handles bursty traffic with modality-aware scheduling and autoscaling to meet tail latency SLOs while minimizing costs. ModServe achieves 3.3-5.5x higher throughput (leading to 25-41.3% cost saving) while meeting SLOs on a 128-GPU cluster with production traces.

Text-to-audio diffusion models produce high-fidelity audio but require tens of function evaluations (NFEs), incurring multi-second latency and limited throughput. We present SoundWeaver, the first training-free, model-agnostic serving system that accelerates text-to-audio diffusion by warm-starting from semantically similar cached audio. SoundWeaver introduces three components: a Reference Selector that retrieves and temporally aligns cached candidates via semantic and duration-aware gating; a Skip Gater that dynamically determines the percentage of NFEs to skip; and a lightweight Cache Manager that maintains cache utility through quality-aware eviction and refinement. On real-world audio traces, SoundWeaver achieves 1.8--3.0 times latency reduction with a cache of only {sim}1K entries while preserving or improving perceptual quality.

Low-Rank Adaptation (LoRA) has become a widely adopted parameter-efficient fine-tuning (PEFT) technique for adapting large language models (LLMs) to downstream tasks. While prior work has explored strategies for integrating LLM training and serving, there still remains a gap in unifying fine-tuning and inference for LoRA-based models. We present Loquetier, a virtualized multi-LoRA framework that seamlessly integrates LoRA fine-tuning and serving within a single runtime. Loquetier introduces two key components: (1) a Virtualized Module that isolates PEFT-based modifications and supports multiple adapters on a shared base model, and (2) an optimized computation flow with a kernel design that merges fine-tuning and inference paths in forward propagation, enabling efficient batching and minimizing kernel invocation overhead. Extensive experiments across three task settings show that Loquetier consistently outperforms existing baselines in both performance and flexibility, achieving up to 3.0times the throughput of the state-of-the-art co-serving system on inference-only tasks and 46.4times higher SLO attainment than PEFT on unified fine-tuning and inference tasks. The implementation of Loquetier is publicly available at https://github.com/NJUDeepEngine/Loquetier.

Top-k sparse attention makes long-context LLM decoding cheap to compute: each step reads only a few thousand selected KV entries rather than the full context. Serving systems, however, typically keep the entire KV cache in GPU HBM so that every position stays selectable, so a request's memory bill still grows with its full context length--decoding hits a capacity wall long before it runs out of compute, and a context whose KV cache exceeds HBM cannot be served at all. We present HiSparse, an exact, indexer-agnostic hierarchical KV cache for sparse-attention serving. HiSparse keeps each request's full KV history in host memory and bounds its decode footprint with a small, fixed-size GPU cache; a fused CUDA kernel resolves each layer's selections--hit detection, LRU replacement, and host-to-device fetches--inside the decode CUDA graph; and, for models that share selections across layers, exact layer-wise prefetching hides roughly half of the remaining miss overhead. Because only KV placement changes, model outputs are unchanged. HiSparse is merged into upstream SGLang and evaluated across three sparse-attention families (DSA, NSA, and Quest) on H200, B200, and GH200 platforms: it improves peak generation throughput by up to 4.7x on long-context workloads while preserving comparable per-token latency and reducing time-to-first-token at high load--and a no-IO oracle shows the resolution mechanism itself adds no measurable per-token cost, leaving host-device IO as the only price of bounded residency.

We study serving retrieval models, specifically late interaction models like ColBERT, to many concurrent users at once and under a small budget, in which the index may not fit in memory. We present ColBERT-serve, a novel serving system that applies a memory-mapping strategy to the ColBERT index, reducing RAM usage by 90% and permitting its deployment on cheap servers, and incorporates a multi-stage architecture with hybrid scoring, reducing ColBERT's query latency and supporting many concurrent queries in parallel.

LLM serving systems typically treat user prompts as monolithic inputs, optimizing inference through decoding tricks or inter-query batching. However, many real-world prompts contain latent semantic parallelism--decomposable structures where subtasks can be executed independently to reduce latency while preserving meaning. We introduce PARALLELPROMPT, the first benchmark for measuring intra-query parallelism in natural user prompts. Our dataset comprises over 37,000 real-world prompts from public LLM chat logs, each annotated with a structured schema capturing task templates, shared context, and iteration inputs. These schemas are extracted using LLM-assisted prompting with rule-based multilingual validation. To evaluate the benefits of decomposition, we provide an execution suite that benchmarks serial vs. parallel strategies, measuring latency, structural adherence, and semantic fidelity. Our results show that intra-query parallelism can be successfully parsed in over 75% of curated datasets, unlocking up to 5x speedups on tasks like translation, comprehension, and comparative analysis, with minimal quality degradation. By releasing this benchmark, curation pipeline, and evaluation suite, we provide the first standardized testbed for studying structure-aware execution in LLM serving pipelines.

LLM serving systems process heterogeneous query workloads where different categories exhibit different characteristics. Code queries cluster densely in embedding space while conversational queries distribute sparsely. Content staleness varies from minutes (stock data) to months (code patterns). Query repetition patterns range from power-law (code) to uniform (conversation), producing long tail cache hit rate distributions: high-repetition categories achieve 40-60% hit rates while low-repetition or volatile categories achieve 5-15% hit rates. Vector databases must exclude the long tail because remote search costs (30ms) require 15--20% hit rates to break even, leaving 20-30% of production traffic uncached. Uniform cache policies compound this problem: fixed thresholds cause false positives in dense spaces and miss valid paraphrases in sparse spaces; fixed TTLs waste memory or serve stale data. This paper presents category-aware semantic caching where similarity thresholds, TTLs, and quotas vary by query category. We present a hybrid architecture separating in-memory HNSW search from external document storage, reducing miss cost from 30ms to 2ms. This reduction makes low-hit-rate categories economically viable (break-even at 3-5% versus 15-20%), enabling cache coverage across the entire workload distribution. Adaptive load-based policies extend this framework to respond to downstream model load, dynamically adjusting thresholds and TTLs to reduce traffic to overloaded models by 9-17% in theoretical projections.

Real-time multimodal applications, including voice agents and interactive video generation, compose heterogeneous models into pipelines whose efficient deployment requires application-specific decisions about placement, streaming, and intra-model parallelism. Existing serving systems and auto-parallelism compilers commit to limited transformations and fixed workload assumptions, so achieving high performance on a new application requires hand-crafting an efficient implementation. We present FlashRT, an agent harness that guides coding agents to lift simple developer-written reference implementations into optimized multi-GPU deployments that flexibly weigh target metrics like latency and throughput. Using a new chain-of-program paradigm, FlashRT directs a generic coding agent through a multi-pass transformation process where an agent transforms the reference into an intermediate representation (IR) to capture data dependencies and persistent-state scopes, validates this IR via a sequential interpreter, and performs static analyses to identify candidate transformations. Then, the agent iteratively implements, verifies, and benchmarks each candidate under a measurement-gated optimization loop to produce effective deployments that span different hardware budgets. Across various applications, including video world models and multimodal LLMs, FlashRT converts reference implementations into highly efficient deployments, delivering up to ~70x latency reduction and 2.8x throughput improvement on NVIDIA B200 GPUs. On AMD MI355X GPUs, FlashRT matches the peak latency reduction while increasing peak throughput improvement to 3.6x, demonstrating that agent-driven optimization can be more scalable on platforms with less mature expert optimization. In fact, for Qwen3-Omni text-to-audio inference, FlashRT reduces response latency by 65% compared to the expert vLLM-Omni implementation on AMD MI355X.

Realistic evaluation of LLM serving systems requires online workloads, dynamic arrivals, queueing, and the serving engine's local scheduling for execution batching, but running such experiments on GPUs is expensive. Existing simulators reduce this cost, but often operate offline or in time-warped mode, re-implement serving-engine schedulers, or require accurate operator/kernel-level latency models. We present LLM-Emu, a serving-native emulator for vLLM that preserves the production HTTP, scheduling, KV-cache, and output-processing paths while replacing only GPU forward execution with profile-sampled latency and synthetic output tokens. Tested on two different GPUs, four model variants, two model families, two attention backends, and both Poisson and bursty ShareGPT workloads, LLM-Emu closely tracks real vLLM serving behavior: TPOT and ITL stay within 4.8% absolute error, E2E latency within 5.3%, and output throughput within 1.9%; TTFT is less stable, with maximum error 10.4%, reflecting its sensitivity to admission and queue state. These results suggest that lightweight, serving-native emulation can support practical online experimentation for LLM-serving systems. LLM-Emu is open sourced at https://github.com/AKafakA/llm-emu.

Deploying a large language model (LLM) inference service remains costly because centralized serving depends on specialized GPU clusters and high-bandwidth interconnects in datacenters. An appealing alternative is to leverage collaborative decentralized GPU pools. However, heterogeneity in GPU and limited interconnected network bandwidth, along with potentially dynamic availability, make efficient scheduling the central challenge in this scenario. In this paper, we present Parallax, a decentralized LLM serving system that turns a pool of heterogeneous GPUs into an efficient inference platform via a two-phase scheduler. Parallax decomposes planning into (i) model allocation, which places layers of each replica across diverse GPUs to jointly optimize latency and throughput under memory and link-bandwidth constraints, and (ii) request-time GPU pipeline selection, which stitches layers from different replicas into end-to-end execution chains that balance load and adapt to current conditions. We implement Parallax and evaluate it on open-source LLMs deployed over real volunteer nodes. Parallax consistently reduces latency and increases throughput relative to decentralized baselines, demonstrating that principled scheduling can make volunteer compute a practical, affordable substrate for LLM inference. Github Repo at: https://github.com/GradientHQ/parallax.

Speculative decoding accelerates Large Language Model (LLM) inference by decoupling draft generation from target verification. While recent parallel drafters efficiently propose long token sequences in a single forward pass, they suffer from rapid acceptance decay due to a lack of inter-token dependencies. Furthermore, indiscriminately verifying these extended blocks wastes critical batch capacity on tokens with high rejection risks, severely degrading throughput in high-concurrency serving systems. We introduce DSpark, a speculative decoding framework that unifies high-throughput parallel generation with adaptive, load-aware verification. To maintain draft quality, DSpark utilizes a semi-autoregressive architecture, coupling a parallel backbone with a lightweight sequential module, to introduce intra-block dependency modeling and mitigate suffix decay. To optimize system efficiency, DSpark employs confidence-scheduled verification, dynamically tailoring the verification length for each request based on estimated prefix survival probabilities and engine-specific throughput profiles. On offline benchmarks across diverse domains, DSpark substantially improves the accepted length over state-of-the-art autoregressive and parallel drafters. When deployed within the DeepSeek-V4 serving system under live user traffic, DSpark successfully mitigates verification waste. Compared to the established production baseline (MTP-1), DSpark accelerates per-user generation speeds by 60 to 85 percent at matched throughput levels. More importantly, by preventing severe throughput degradation under strict interactivity constraints, it enables performance tiers that were previously unattainable, shifting the Pareto frontier of our serving system.

Two widely adopted techniques for LLM inference serving systems today are hybrid batching and disaggregated serving. A hybrid batch combines prefill and decode tokens of different requests in the same batch to improve resource utilization and throughput at the cost of increased latency per token. In contrast, disaggregated serving decouples compute-bound prefill and bandwidth-bound decode phases to optimize for service level objectives (SLOs) at the cost of resource under-utilization and KV-cache transfer overheads. To address the limitations of these techniques, we propose RAPID-Serve: a technique to concurrently execute prefill and decode on the same GPU(s) to meet latency SLOs while maintaining high throughput and efficient resource utilization. Furthermore, we propose Adaptive Resource Management for runtime compute resource allocation, optionally leveraging CU masking (a fine-grained Compute Unit partitioning feature on AMD InstinctTM GPUs). RAPID-Serve provides up to 4.1x (average 1.7x) unconstrained throughput improvement and 32x and higher (average 4.9x) throughput improvement under SLO constraints, showing it as an effective strategy compared to the state-of-the-art approaches, particularly in resource-constrained environments.

AI coding agents like GitHub Copilot, Claude Code, and Codex interleave multi-step LLM inference with tool execution, creating a workload different from chatbots. We present the first production-scale characterization of this workload using sampled GitHub Copilot traces from June 2026, comprising 3.2M users, 13M sessions, 761M LLM calls, and 95T tokens. Our analysis reveals distinctive workload properties with important systems implications. For example, agentic coding sessions consist of sparse user-initiated turns, each unfolding into an autonomous agent loop of LLM calls almost always coupled with tool execution. This structure yields KV cache hit rates averaging 90% within a turn, but falling to 55\% across turn boundaries and drastically invalidated after events like model switches or context compaction. Diverse workflows and user behaviors are observed with variable and long-tailed token consumption, time span, and tool calls. We highlight the difference between quick agentic turnaround times and the minutes-long user idle periods at turn boundaries, and design a lightweight idle-time predictor that captures 86-90\% of total idle time, enabling proactive decisions for efficient resource orchestration. These findings challenge assumptions underlying current LLM-serving systems and provide an empirical foundation for agent-native infrastructure.

The advent of large language models (LLMs) has transformed text-based services, enabling capabilities ranging from real-time translation to AI-driven chatbots. However, existing serving systems primarily focus on optimizing server-side aggregate metrics like token generation throughput, ignoring individual user experience with streamed text. As a result, under high and/or bursty load, a significant number of users can receive unfavorable service quality or poor Quality-of-Experience (QoE). In this paper, we first formally define QoE of text streaming services, where text is delivered incrementally and interactively to users, by considering the end-to-end token delivery process throughout the entire interaction with the user. Thereafter, we propose Andes, a QoE-aware serving system that enhances user experience for LLM-enabled text streaming services. At its core, Andes strategically allocates contended GPU resources among multiple requests over time to optimize their QoE. Our evaluations demonstrate that, compared to the state-of-the-art LLM serving systems like vLLM, Andes improves the average QoE by up to 3.2times under high request rate, or alternatively, it attains up to 1.6times higher request rate while preserving high QoE.

In Large Language Model (LLM) inference, the output length of an LLM request is typically regarded as not known a priori. Consequently, most LLM serving systems employ a simple First-come-first-serve (FCFS) scheduling strategy, leading to Head-Of-Line (HOL) blocking and reduced throughput and service quality. In this paper, we reexamine this assumption -- we show that, although predicting the exact generation length of each request is infeasible, it is possible to predict the relative ranks of output lengths in a batch of requests, using learning to rank. The ranking information offers valuable guidance for scheduling requests. Building on this insight, we develop a novel scheduler for LLM inference and serving that can approximate the shortest-job-first (SJF) schedule better than existing approaches. We integrate this scheduler with the state-of-the-art LLM serving system and show significant performance improvement in several important applications: 2.8x lower latency in chatbot serving and 6.5x higher throughput in synthetic data generation. Our code is available at https://github.com/hao-ai-lab/vllm-ltr.git

Agentic LLM applications interleave LLM generation requests with tool calls. These tool calls break the continuity of the workflow by creating pauses between LLM requests, bringing many challenges for the serving system, especially under multi-turn scenarios. Each pause potentially causes KV cache eviction and extra waiting time before entering the continuous batch for the following LLM request. Since these pauses happen for each call, this problem becomes increasingly severe as turn number grow for agentic programs. Previous works either fail to incorporate information from the tool call, evicting KV cache that leads to repetitive prefill or loading, or ignore the continuity of a multi-turn program, creating waiting time between turns that increases per-request latency. We present Continuum, a serving system to optimize job completion time for multi-turn agent workloads by combining tool-aware KV cache timeout with program-level scheduling. By predicting tool call durations in agentic workflows, Continuum selectively pins the KV cache in GPU memory with a time-to-live value based on total turn number. When combined with program-level first-come-first-serve, Continuum prevents scheduling bubbles, preserves multi-turn continuity, and optimizes for throughput for complex agentic workflows. By modeling the variability of tool call and agent program continuity, Continuum outperforms state-of-the-art baselines. Our evaluation on real-world agentic workloads (SWE-Bench and BFCL) with Llama-3.1 8B/70B models shows that Continuum significantly improves the average job completion times, and remains performant across different hardware setups and DRAM offloading schemes. Preview code is available at: https://github.com/Hanchenli/vllm-continuum

Long-horizon agents increasingly reuse their KV cache as memory: a serving system keeps a subset of cached entries and drops the rest. Eviction and episodic-memory schemes therefore rest on a premise rarely tested directly, that a retained event is still informative once the observations that produced it are gone. We test it by omitting one earlier observation from what is served, across otherwise identical agent histories. Among items sensitive to that observation, the answer overwhelmingly follows the omitted value, though no served span says which value is correct. We call this semantic materialization: a downstream event's cached rows act as an independently servable view of computation whose inputs are gone. It can also be written on purpose. A deliberately phrased, answer-free event raises donor-aligned recovery from 6% to 51% on Qwen3-8B without ever naming the value, whereas passively harvesting natural mentions from long-term dialog yields no detected advantage. What such a row carries is specific and bounded. Compact state survives, larger payloads decay toward chance, and whether a construction writes at all turns on phrasing rather than on meaning alone, so two phrasings the model comprehends equally well can diverge sharply. The result is a memory contract for sparse event-KV serving: what to write, where it lands, and what survives once the source is gone. For anyone who evicts the corollary is that dropping a source event and observing no accuracy loss does not show the source was unnecessary.

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.

The rapid proliferation of Large Language Models (LLMs) has been a driving force in the growth of cloud-based LLM services, which are now integral to advancing AI applications. However, the dynamic auto-regressive nature of LLM service, along with the need to support exceptionally long context lengths, demands the flexible allocation and release of substantial resources. This presents considerable challenges in designing cloud-based LLM service systems, where inefficient management can lead to performance degradation or resource wastage. In response to these challenges, this work introduces DistAttention, a novel distributed attention algorithm that segments the KV Cache into smaller, manageable units, enabling distributed processing and storage of the attention module. Based on that, we propose DistKV-LLM, a distributed LLM serving system that dynamically manages KV Cache and effectively orchestrates all accessible GPU and CPU memories spanning across the data center. This ensures a high-performance LLM service on the cloud, adaptable to a broad range of context lengths. Validated in a cloud environment with 32 NVIDIA A100 GPUs in configurations from 2 to 32 instances, our system exhibited 1.03-2.4x end-to-end throughput improvements and supported context lengths 2-19x longer than current state-of-the-art LLM service systems, as evidenced by extensive testing across 18 datasets with context lengths up to 1,900K.

Context retrieval systems for LLM inference face a critical challenge: high retrieval latency creates a fundamental tension between waiting for complete context (poor time-to-first-token) and proceeding without it (reduced quality). Streaming context incrementally--overlapping retrieval with inference--can mitigate this latency, but doing so with concurrent requests introduces new challenges: requests contend for GPU compute and memory, and scheduling must adapt to dynamic context arrivals. We present Stream2LLM, a streaming-aware LLM serving system for concurrent prefill-decode disaggregated deployments. Stream2LLM introduces adaptive scheduling and preemption for two distinct retrieval patterns: append-mode (progressive context accumulation) and update-mode (iterative refinement with cache invalidation). It decouples scheduling decisions from resource acquisition, enabling flexible preemption strategies guided by hardware-specific cost models, and uses longest common prefix matching to minimize redundant computation when input changes dynamically. To evaluate Stream2LLM, we collect two large-scale, real-world streaming workloads based on web crawling and approximate nearest neighbor search. Our evaluation demonstrates that streaming architecture delivers up to 11x TTFT improvements, with cost-aware scheduling providing critical benefits under memory pressure, all while maintaining throughput parity with non-streaming baselines. Code: https://github.com/rajveerb/stream2llm/tree/mlsys_artifact

We introduce Mirage Persistent Kernel (MPK), the first compiler and runtime system that automatically transforms multi-GPU model inference into a single high-performance megakernel. MPK introduces an SM-level graph representation that captures data dependencies at the granularity of individual streaming multiprocessors (SMs), enabling cross-operator software pipelining, fine-grained kernel overlap, and other previously infeasible GPU optimizations. The MPK compiler lowers tensor programs into highly optimized SM-level task graphs and generates optimized CUDA implementations for all tasks, while the MPK in-kernel parallel runtime executes these tasks within a single mega-kernel using decentralized scheduling across SMs. Together, these components provide end-to-end kernel fusion with minimal developer effort, while preserving the flexibility of existing programming models. Our evaluation shows that MPK significantly outperforms existing kernel-per-operator LLM serving systems by reducing end-to-end inference latency by up to 1.7x, pushing LLM inference performance close to hardware limits. MPK is publicly available at https://github.com/mirage-project/mirage.

The deployment and scaling of large language models (LLMs) have become critical as they permeate various applications, demanding high-throughput and low-latency serving systems. Existing frameworks struggle to balance these requirements, especially for workloads with long prompts. This paper introduces DeepSpeed-FastGen, a system that employs Dynamic SplitFuse, a novel prompt and generation composition strategy, to deliver up to 2.3x higher effective throughput, 2x lower latency on average, and up to 3.7x lower (token-level) tail latency, compared to state-of-the-art systems like vLLM. We leverage a synergistic combination of DeepSpeed-MII and DeepSpeed-Inference to provide an efficient and easy-to-use serving system for LLMs. DeepSpeed-FastGen's advanced implementation supports a range of models and offers both non-persistent and persistent deployment options, catering to diverse user scenarios from interactive sessions to long-running applications. We present a detailed benchmarking methodology, analyze the performance through latency-throughput curves, and investigate scalability via load balancing. Our evaluations demonstrate substantial improvements in throughput and latency across various models and hardware configurations. We discuss our roadmap for future enhancements, including broader model support and new hardware backends. The DeepSpeed-FastGen code is readily available for community engagement and contribution.

LLM agents often degrade over long episodes: as trajectories grow, they revisit explored states, repeat failed actions, and lose strategies that previously worked. Test-time training (TTT) offers a way to adapt model weights to the evolving task state, but existing LLM TTT methods largely adapt once to a fixed input. We study continuous TTT in multi-turn agent episodes, where each update changes the policy that generates later training text. This creates a self-training loop that helps when new trajectory information appears, but can amplify drift when the agent gets stuck and repeatedly trains on similar text. We find that update-text repetition distinguishes these regimes and introduce Agentic Test-Time Training (aTTT), a token-level reweighting method that downweights the loss on tokens appearing in repeated n-grams from prior updates while leaving novel tokens fully weighted. To run such updates inside live episodes, we build a concurrent serving system using vLLM's runtime LoRA API, limiting overhead to 1.9times the no-TTT cost. aTTT improves success by up to 5.0 points on ALFWorld and 4.9 points on SWE-bench Lite. The gains concentrate where models already have task competence but drift over long trajectories, suggesting that aTTT mainly preserves existing competence rather than teaching new abilities.

Large Language Models (LLMs) demonstrate substantial accuracy gains when augmented with reasoning modes such as chain-of-thought and inference-time scaling. However, reasoning also incurs significant costs in inference latency and token usage, with environmental and financial impacts, which are unnecessary for many simple prompts. We present a semantic router that classifies queries based on their reasoning requirements and selectively applies reasoning only when beneficial. Our approach achieves a 10.2 percentage point improvement in accuracy on the MMLU-Pro benchmark while reducing response latency by 47.1% and token consumption by 48.5% compared to direct inference with vLLM. These results demonstrate that semantic routing offers an effective mechanism for striking a balance between accuracy and efficiency in open-source LLM serving systems

Modern LLM agents increasingly rely on dynamic structured generation, such as tool calling and response protocols. Unlike traditional structured generation with static structures, these workloads vary both across requests and within a request, posing new challenges to existing engines. We present XGrammar-2, a structured generation engine for dynamic agentic workloads. Our design is based on two key ideas: first-class support for tag-triggered structure switching, and fine-grained reuse across requests with different output structures. Concretely, XGrammar-2 introduces TagDispatch for dynamic structural dispatching and Cross-Grammar Cache for substructure-level cache reuse across grammars. It further improves efficiency with an Earley-based adaptive token mask cache, just-in-time compilation, and repetition state compression. Experiments show that XGrammar-2 achieves over 6x faster compilation than prior structured generation engines, and incurs near-zero end-to-end overhead in modern LLM serving systems.

The rapid expansion of Transformer-based large language models has dramatically increased the need for high-performance GPUs. As a result, there is growing demand for fast, accurate, and widely generalizable GPU performance models to support next-generation hardware selection and system-level exploration. However, current data-driven methods are limited, exhibiting poor generalization across hardware and inadequate modeling of complex production-level kernels common in modern inference stacks. To address these issues, we present PipeWeave, a unified GPU modeling framework. This approach first employs an analytical model to quantify a given kernel's demands on the GPU's heterogeneous instruction pipelines. These analytical features are then fed into a machine learning (ML) model to capture complex cross-pipeline interactions and resource dependencies, enabling high-fidelity performance prediction. Our evaluation across 11 GPU types from four generations of major architectures on two widely-used serving systems demonstrates that PipeWeave delivers high fidelity and strong generalizability. It achieves accurate predictions, with only 6.1% average error at the kernel level and 8.5% for end-to-end inference -- reducing the error of state-of-the-art methods by 6.7x and 4.4x, respectively. We also demonstrate PipeWeave's value "beyond simulation" by utilizing its performance ceiling to diagnose implementation shortcomings and guide the optimization of a production fused MoE Triton kernel, achieving up to 1.7x speedup. Code is available https://github.com/zksainx/pipeweave.

Agentic inference now dominates the LLM inference landscape, requiring LLMs to actively engage in multi-turn interactions with tool-calling capabilities. This introduces a more complex workload for the underlying inference system: serving stages such as prefill and decode exhibit substantially different behaviors and demand distinct compute and memory-bandwidth capabilities. As a result, a single homogeneous GPU system now struggles to support agentic inference, motivating an industry shift toward heterogeneous systems with disaggregated serving capabilities, such as the emerging Vera-Rubin platform with GPUs and Groq LPUs. However, the question of what the optimal hardware should look like for each component in a heterogeneous system remains underexplored. To this end, we propose a novel simulation framework for disaggregated serving, termed HeteroPanacea, that enables system-level simulation across three dimensions: 1) disaggregated quantization, 2) automated intra- and inter-device parallelization scheduling, and 3) PDAF (prefill-decode-attention-FFN) NPU architectural heterogeneity. By combining these three axes, we provide a cross-stack simulation framework for future heterogeneous agentic serving systems. We confirm the benefit of Prefill Decode disaggregation, simulating increased serving throughput by up to 75\% compared to traditional serving with current GPUs and demonstrate 4 way Prefill Decode Attention FFN disaggregation is the most consistent for increasing throughput across different models, assuming custom NPUs. We also investigate the relationship between model architecture and gain from disaggregation by running a set of ablation studies.

Autoregressive (AR) language models generate text one token at a time, even when consecutive tokens are highly predictable given earlier context. We introduce MARS (Mask AutoRegreSsion), a lightweight fine-tuning method that teaches an instruction-tuned AR model to predict multiple tokens per forward pass. MARS adds no architectural modifications, no extra parameters, and produces a single model that can still be called exactly like the original AR model with no performance degradation. Unlike speculative decoding, which maintains a separate draft model alongside the target, or multi-head approaches such as Medusa, which attach additional prediction heads, MARS requires only continued training on existing instruction data. When generating one token per forward pass, MARS matches or exceeds the AR baseline on six standard benchmarks. When allowed to accept multiple tokens per step, it maintains baseline-level accuracy while achieving 1.5-1.7x throughput. We further develop a block-level KV caching strategy for batch inference, achieving up to 1.71x wall-clock speedup over AR with KV cache on Qwen2.5-7B. Finally, MARS supports real-time speed adjustment via confidence thresholding: under high request load, the serving system can increase throughput on the fly without swapping models or restarting, providing a practical latency-quality knob for deployment.

Effective user representations are pivotal in personalized advertising. However, stringent constraints on training throughput, serving latency, and memory, often limit the complexity and input feature set of online ads ranking models. This challenge is magnified in extensive systems like Meta's, which encompass hundreds of models with diverse specifications, rendering the tailoring of user representation learning for each model impractical. To address these challenges, we present Scaling User Modeling (SUM), a framework widely deployed in Meta's ads ranking system, designed to facilitate efficient and scalable sharing of online user representation across hundreds of ads models. SUM leverages a few designated upstream user models to synthesize user embeddings from massive amounts of user features with advanced modeling techniques. These embeddings then serve as inputs to downstream online ads ranking models, promoting efficient representation sharing. To adapt to the dynamic nature of user features and ensure embedding freshness, we designed SUM Online Asynchronous Platform (SOAP), a latency free online serving system complemented with model freshness and embedding stabilization, which enables frequent user model updates and online inference of user embeddings upon each user request. We share our hands-on deployment experiences for the SUM framework and validate its superiority through comprehensive experiments. To date, SUM has been launched to hundreds of ads ranking models in Meta, processing hundreds of billions of user requests daily, yielding significant online metric gains and improved infrastructure efficiency.

Context-heavy agents place unusual pressure on the key-value (KV) cache: long prefixes are reused across many short turns, while concurrency determines whether the serving system can keep GPUs utilized. We study 4-bit KV-cache compression for this setting, using TurboQuant-style rotation and codebook quantization as a quality anchor and vLLM FP8 KV caching as the deployment anchor. We report three contributions. First, we frame 4-bit KV caching around multi-round agent workloads where task quality, cache residency, and serving throughput must be measured jointly. Second, we describe the practical design choices needed to make the 4-bit path robust, including asymmetric K/V treatment, Walsh-Hadamard rotation, QJL removal, and block-scale variants. Third, we present serving optimizations on AMD GPUs, including optimized decode-attention kernels and UltraQuant, an FP4 approximation path that uses FP8 queries, FP4 KV tensors, UE8M0 group scales, and native scaled-MFMA support on CDNA4. On a long-context, multi-turn agentic workload, UltraQuant cuts P50 time-to-first-token by 3.47x in the cache-pressured late rounds (2.3x across all rounds) and raises output throughput by 1.63x over the FP8 KV baseline.

Mixture-of-experts models make nearly trillion-parameter capacity accessible with sparse per-token computation, provided that the serving system can distribute the weights and coordinate their execution. We present Cascadia's resident execution of Inkling, a 975B-total/41B-active-parameter model, on eleven Intel Core Ultra X7 358H AI PCs, each with 64 GB of memory, Arc B390 integrated graphics and gigabit Ethernet. We contribute a custom resident MoE engine that preserves Inkling's routing rules, constructs compressed graphs for OpenVINO's fused iGPU primitives, and coordinates FP16 expert computation with FP32 output restoration. The engine fits six consecutive decoder layers per machine and represents dense feed-forward blocks as all-active expert slices, reducing measured dense-layer call time from approximately 8.1 to 4.5 ms. A streaming pipeline coordinates concurrent generation, while captured-state draft evaluation measures agreement with the deployed numerical path. Paired measurements at fifteen concurrency levels from 1 to 176 streams reach 60.29 aggregate decode tokens/s at 88 streams, with 46.87 tokens/s over the complete serving phases. At fifteen streams, median first-token latency is 6.05 s. Raising the context budget from the 1,024-position default, real prompts of 1k to 64k tokens recover the embedded code in all 19 measured answers, with first-token time growing as aN+bN^2 and decode latency growing approximately linearly, both bounded by a single-threaded CPU attention loop rather than by memory, which holds 512k positions per stream. Evaluation on captured fleet states separates the effects of vocabulary selection and weight quantization on draft agreement. Together, these contributions establish an execution and evaluation approach for large sparse models on distributed client systems with shared CPU-GPU memory.

Transformer-based large language models (LLMs) demonstrate impressive performance across various natural language processing tasks. Serving LLM inference for generating long contents, however, poses a challenge due to the enormous memory footprint of the transient state, known as the key-value (KV) cache, which scales with the sequence length and batch size. In this paper, we present InfiniGen, a novel KV cache management framework tailored for long-text generation, which synergistically works with modern offloading-based inference systems. InfiniGen leverages the key insight that a few important tokens that are essential for computing the subsequent attention layer in the Transformer can be speculated by performing a minimal rehearsal with the inputs of the current layer and part of the query weight and key cache of the subsequent layer. This allows us to prefetch only the essential KV cache entries (without fetching them all), thereby mitigating the fetch overhead from the host memory in offloading-based LLM serving systems. Our evaluation on several representative LLMs shows that InfiniGen improves the overall performance of a modern offloading-based system by up to 3.00x compared to prior KV cache management methods while offering substantially better model accuracy.

Deep neural network (DNN) inference has become an important part of many data-center workloads. This has prompted focused efforts to design ever-faster deep learning accelerators such as GPUs and TPUs. However, an end-to-end DNN-based vision application contains more than just DNN inference, including input decompression, resizing, sampling, normalization, and data transfer. In this paper, we perform a thorough evaluation of computer vision inference requests performed on a throughput-optimized serving system. We quantify the performance impact of server overheads such as data movement, preprocessing, and message brokers between two DNNs producing outputs at different rates. Our empirical analysis encompasses many computer vision tasks including image classification, segmentation, detection, depth-estimation, and more complex processing pipelines with multiple DNNs. Our results consistently demonstrate that end-to-end application performance can easily be dominated by data processing and data movement functions (up to 56% of end-to-end latency in a medium-sized image, and sim 80% impact on system throughput in a large image), even though these functions have been conventionally overlooked in deep learning system design. Our work identifies important performance bottlenecks in different application scenarios, achieves 2.25times better throughput compared to prior work, and paves the way for more holistic deep learning system design.

The increasing context window size in large language models (LLMs) has improved their ability to handle complex, long-text tasks. However, as the conversation rounds continue, it is required to store a large amount of KV cache in GPU memory, which significantly affects the efficiency and even availability of the model serving systems. This paper analyzes dialogue data from real users and discovers that the LLM inference manifests a watershed layer, after which the distribution of round-level attention shows notable similarity. We propose Round Attention, a novel round-level attention mechanism that only recalls and computes the KV cache of the most relevant rounds. The experiments show that our method saves 55\% memory usage without compromising model performance.

Batch inference for agentic workloads stresses the GPU key-value (KV) cache in a sustained and cumulative manner, often causing severe throughput degradation well before memory capacity is exhausted. We identify this phenomenon as middle-phase thrashing, a previously under-characterized pathology in which cache efficiency collapses as long-lived agents accumulate state over time. We argue that mitigating this pathology requires moving beyond reactive, request-level cache management to proactive, agent-level admission control. Drawing inspiration from congestion control in distributed systems, we view the KV cache as a shared resource whose efficient utilization depends on feedback-driven regulation. Based on this insight, we present CONCUR, a lightweight control layer that regulates agent admission to bound aggregate cache pressure while preserving execution continuity. CONCUR adapts a cache-aware control algorithm to dynamically adjust the number of active agents using runtime cache signals. Across large models and real-world agent workloads, CONCUR prevents middle-phase thrashing and improves batch inference throughput by up to 4.09x on Qwen3-32B and 1.9x on DeepSeek-V3, while remaining compatible with existing LLM serving systems.

Large Multimodal Models (LMMs) have shown significant progress in various complex vision tasks with the solid linguistic and reasoning capacity inherited from large language models (LMMs). Low-rank adaptation (LoRA) offers a promising method to integrate external knowledge into LMMs, compensating for their limitations on domain-specific tasks. However, the existing LoRA model serving is excessively computationally expensive and causes extremely high latency. In this paper, we present an end-to-end solution that empowers diverse vision tasks and enriches vision applications with LoRA LMMs. Our system, VaLoRA, enables accurate and efficient vision tasks by 1) an accuracy-aware LoRA adapter generation approach that generates LoRA adapters rich in domain-specific knowledge to meet application-specific accuracy requirements, 2) an adaptive-tiling LoRA adapters batching operator that efficiently computes concurrent heterogeneous LoRA adapters, and 3) a flexible LoRA adapter orchestration mechanism that manages application requests and LoRA adapters to achieve the lowest average response latency. We prototype VaLoRA on five popular vision tasks on three LMMs. Experiment results reveal that VaLoRA improves 24-62% of the accuracy compared to the original LMMs and reduces 20-89% of the latency compared to the state-of-the-art LoRA model serving systems.

Efficient and scalable agentic intelligence requires models that can deliver both low-latency responses and strong reasoning capabilities while remaining practical to train, serve, and deploy. In this report, we present Ling-2.6 and Ring-2.6, a family of models designed to address this challenge at scale. Ling-2.6 is optimized for instant response generation and high capability per output token, whereas Ring-2.6 is tailored for deeper reasoning and more advanced agentic workflows. Instead of training from scratch, we upgrade the Ling-2.0 base model through architectural migration pre-training and large-scale post-training. This upgrade is guided by a unified co-design of model architecture, optimization objectives, serving systems, and agent training environments, enabling improvements in both model capability and deployment efficiency. At the architectural level, we introduce a hybrid linear attention design that integrates Lightning Attention with MLA, improving the efficiency of long-context training and decoding. To further enhance token efficiency, we optimize capability per output token through Evolutionary Chain-of-Thought, Linguistic Unit Policy Optimization, bidirectional preference alignment, and shortest-correct-response distillation. For agentic capabilities, we propose KPop, a reinforcement learning framework designed to support stable training of Ring-2.6-1T on large-scale environment-grounded data. KPop improves training efficiency through asynchronous scheduling across coding, search, tool use, and workflow execution, enabling scalable learning from complex agent-environment interactions. Together, Ling-2.6 and Ring-2.6 provide a practical pathway toward efficient, scalable, and open agentic systems. We open-source all checkpoints in the 2.6 family to support further research and development in practical agentic intelligence.

Long-horizon LLM agents accumulate sessions of up to millions of tokens, far more key-value (KV) cache than one GPU holds, so serving systems keep a small budget of tokens and evict the rest. Eviction methods differ in which tokens they keep but share one goal: that the tokens a later step needs are still cached. We show this is not enough. In 100K-token coding sessions on Qwen3-8B with a 2,048-token budget, a planner-guided policy that keeps over 99% of the needed tokens resident still fails late steps increasingly often: its accuracy falls from 93% to 64% as the gap between a definition and its use grows from 2K to 90K tokens, at residency 0.996. The needed tokens are resident but unretrievable: what grows is their rotary-position distance to the query. We present PACE (Planner-Aware Context Engine), a KV-cache engine that couples plan-aware retention, in which the agent's planner tells the cache which context future steps will read, with bounded positions, which renumber kept tokens so their rotary distance to the query stays below 8K at any session length. In a pre-registered evaluation on fresh tasks, PACE passes 97% of hidden unit tests at 100K tokens, against 42% for H2O and 3% for SnapKV under the same budget, and needs both components: either alone reaches 63% (the combination beats each, p < 10^-4). The result holds with length: in 1M- and 2M-token sessions on one 24 GB GPU, with definitions written 0.9M and 1.8M tokens before use, PACE passes 99% and 100% of checks and recalls every session fact, while bounded positions without foresight falls from 33% to 13%; PACE holds under 0.7 GB of KV state where the full cache would need 147-295 GB. Renumbering is exact, costs no measurable perplexity, and adds 9% wall time. On Mistral-7B, whose coding ability caps it at 40% even with nothing evicted, PACE stays at that ceiling while retention alone falls below it.

In the rapidly evolving landscape of artificial intelligence (AI), generative large language models (LLMs) stand at the forefront, revolutionizing how we interact with our data. However, the computational intensity and memory consumption of deploying these models present substantial challenges in terms of serving efficiency, particularly in scenarios demanding low latency and high throughput. This survey addresses the imperative need for efficient LLM serving methodologies from a machine learning system (MLSys) research perspective, standing at the crux of advanced AI innovations and practical system optimizations. We provide in-depth analysis, covering a spectrum of solutions, ranging from cutting-edge algorithmic modifications to groundbreaking changes in system designs. The survey aims to provide a comprehensive understanding of the current state and future directions in efficient LLM serving, offering valuable insights for researchers and practitioners in overcoming the barriers of effective LLM deployment, thereby reshaping the future of AI.

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 1.32times speedup for BF16 KV cache transfer, 1.30times speedup for TTFT, and 1.23times increase in Request Throughput. The same approach extends to FP8 KV caches, providing up to 1.14times compression over native E5M2. Code is available at https://github.com/Intelligent-Microsystems-Lab/SplitZip

Large language model (LLM) serving requires substantial memory to store model weights and KV caches. As models grow larger and contexts become longer, memory capacity and bandwidth increasingly become bottlenecks for serving performance. Agentic workloads compound this pressure through repeated interactions over growing contexts, making it increasingly important to retain KV state for reuse. High-bandwidth flash (HBF) offers a way to expand accelerator memory capacity for large language model (LLM) serving, but its access costs and limited write endurance complicate its use. We evaluate HBF for high-throughput agentic serving across system design and scheduling choices to understand when additional capacity improves serving performance and energy efficiency. We introduce an HBM-HBF-host hierarchical storage system and buffered cache-aware scheduling, and use trace-driven simulations to analyze their effects on performance, energy consumption, and HBF write lifetime. Across the evaluated workloads, the fastest HBF-augmented systems reduce completion time by 36.1-87.7% relative to HBM-only systems. Modeled energy savings reach 59.1%, with benefits depending on the workload and weight placement. Buffered cache-aware scheduling extends estimated HBF write lifetime from 1.21 to 14.82 years in the evaluated configuration. These results demonstrate the importance of coordinating data placement and scheduling to improve serving efficiency while sustaining a practical HBF write lifetime.

Industrial advertising recommender systems are continually improved through architecture modifications, yet production iteration remains expert-intensive because coordinated changes to model topology, feature configuration, and interaction modules must satisfy strict interface, resource, and serving constraints. AutoML is limited to predefined search spaces, while generic coding agents verify runnability rather than recommender-specific semantic validity. Executable candidates may therefore violate architectural contracts, while the lack of structured reuse of semantic diagnostics and evaluation outcomes can lead to repeated invalid or ineffective modifications. We present NOVA, a verification-aware agent harness that organizes production architecture modification as multi-round search over concrete implementations within a fixed evaluation budget. At each round, NOVA generates multiple candidates under production constraints, rejects semantic violations, and ranks the valid survivors for local testing and offline evaluation. Across rounds, trajectory memory synthesizes semantic diagnostics, local-test outcomes, and offline metric changes into modification directions and forbidden patterns that guide subsequent search. Under the same maximum offline-evaluation budget for automated methods, NOVA achieves the highest effective pass rate, reaching 53.3% on ScaleUp and 51.7% on Literature-to-Production tasks. In a production A/B test covering 5% of traffic in an advertising system serving over one billion users, the selected Literature-to-Production candidate yields GMV gains of +1.25%, +1.70%, and +2.02% across three major pCVR objectives, with corresponding relative reductions in absolute pCVR bias of 58.8%, 66.7%, and 37.3%, respectively.

Mixture-of-experts (MoE) language models often exceed the memory of a single GPU. Expert offloading keeps most experts in host memory and loads them on demand, so decoding speed depends on how many experts each token must fetch. Caching and prefetching reduce this cost only as far as the routing allows. Router-only fine-tuning can reshape the routing to reuse experts, but it keeps the experts frozen, so they cannot adapt to the tokens the new routing sends them. We propose MaskCoFT, a masked co-adaptive fine-tuning method that trains routers and experts together with the cross-entropy loss alone. During fine-tuning, a learnable binary mask restricts the Top-K routing of each layer to a subset of experts, and the experts adapt to the tokens redirected to them. At inference, the learned mask becomes a soft prior that re-ranks experts, so every expert remains selectable. We simulate a GPU cache of 4 experts per layer for Mixtral-8x7B and 12 for DeepSeek-V2-Lite. MaskCoFT cuts expert fetches per token by 23.7% and 10.1% relative to the base model. In real offloading system serving, it lowers the time per output token by up to 16.4% and 5.5%, respectively. Its average accuracy over nine benchmarks stays above the base model by 0.92 and 0.53 points.

Industrial recommender systems face two fundamental limitations under the log-driven paradigm: (1) knowledge poverty in ID-based item representations that causes brittle interest modeling under data sparsity, and (2) systemic blindness to beyond-log user interests that constrains model performance within platform boundaries. These limitations stem from an over-reliance on shallow interaction statistics and close-looped feedback while neglecting the rich world knowledge about product semantics and cross-domain behavioral patterns that Large Language Models have learned from vast corpora. To address these challenges, we introduce ReaSeq, a reasoning-enhanced framework that leverages world knowledge in Large Language Models to address both limitations through explicit and implicit reasoning. Specifically, ReaSeq employs explicit Chain-of-Thought reasoning via multi-agent collaboration to distill structured product knowledge into semantically enriched item representations, and latent reasoning via Diffusion Large Language Models to infer plausible beyond-log behaviors. Deployed on Taobao's ranking system serving hundreds of millions of users, ReaSeq achieves substantial gains: >6.0% in IPV and CTR, >2.9% in Orders, and >2.5% in GMV, validating the effectiveness of world-knowledge-enhanced reasoning over purely log-driven approaches.

AI agent inference is driving an inference heavy datacenter future and exposes bottlenecks beyond compute - especially memory capacity, memory bandwidth and high-speed interconnect. We introduce two metrics - Operational Intensity (OI) and Capacity Footprint (CF) - that jointly explain regimes the classic roofline analysis misses, including the memory capacity wall. Across agentic workflows (chat, coding, web use, computer use) and base model choices (GQA/MLA, MoE, quantization), OI/CF can shift dramatically, with long context KV cache making decode highly memory bound. These observations motivate disaggregated serving and system level heterogeneity: specialized prefill and decode accelerators, broader scale up networking, and decoupled compute-memory enabled by optical I/O. We further hypothesize agent-hardware co design, multiple inference accelerators within one system, and high bandwidth, large capacity memory disaggregation as foundations for adaptation to evolving OI/CF. Together, these directions chart a path to sustain efficiency and capability for large scale agentic AI inference.

Large language models (LLMs) are reshaping recommender systems by enabling richer modeling of users, content, and context directly in natural language. At Netflix, we are exploring this direction through GenRec, an LLM-backed recommendation ranker built on top of an in-house foundational LLM. GenRec follows a two-phase framework: Phase 1 adapts an open-source LLM to Netflix data, developing deep understanding of the catalog and member behavior while balancing capabilities such as content understanding and instruction following. Phase 2 post-trains this foundation model with recommendation-ranking specific data, labels, and reward signals, aiming to align the ranker with business requirements and long-term member satisfaction. This paper focuses on Phase 2 and the transition from a traditional discriminative ranker with thousands of engineered features to an LLM-backed ranker driven by verbalized user histories and context. We describe our design for input verbalization and context engineering, post-training data construction, reward integration, model architecture, and a cost-constrained serving design based on a prefill-only inference approach. We report results from a large-scale A/B test comparing GenRec against the current production ranker model, where we show that a GenRec model trained with substantially fewer Phase-2 labeled training examples and input signals can achieve statistically significant gains in offline and online metrics. We discuss how LLM-backed recommenders could shift the recommendation paradigm: from feature engineering to context engineering, and from bespoke architectures to shared foundation backbones. We also outline practical lessons for serving such systems under real-world resource constraints.

AI agents are increasingly transacting on behalf of users -- delegating tasks, spending budgets, and negotiating with unfamiliar counterparties. Unlike human marketplaces, which operate under institutional designs refined over centuries, the rules governing emerging agent marketplaces are being built ad-hoc, and early choices tend to lock in. Understanding what dynamics these rules produce is urgent. We present diagon, a programmable market system serving as a rule-agnostic experimental testbed for institutional design in emerging agent cognitive-labour markets. diagon makes institutional choices experimentally manipulable: heterogeneous tool-using agents post jobs, bid, negotiate, execute, pay, and accumulate reputation, with every mechanism end-to-end observable. We instantiate one market form to demonstrate diagon. We find that market exchange generates more productivity gains over self-sufficient agents, but these gains depend strongly on institutional structure; for example, interventions such as identity transparency and stronger competitive selection can degrade market performance rather than improve it. These findings highlight concrete design requirements for the economic infrastructure of the agent era. Code and data are available at https://github.com/assassin808/diagon.

Deploying large language models for legal question answering raises challenges that general-purpose leaderboards do not capture, particularly for low-resource languages and under hard operational constraints. We report on building and operating a retrieval-augmented (RAG) legal assistant for Uzbek that must run in two regimes: a managed cloud service that maximizes answer quality within a per-token cost ceiling, and an on-premises deployment for clients whose legal data may not leave their infrastructure, restricting us to open-weight models on limited local hardware under latency constraints. Because no evaluation existed for this setting, we build two domain benchmarks: a retrieval benchmark of 178 expert-annotated legal queries with gold provision spans, and an end-to-end benchmark of 504 expert-curated question--answer pairs scored by an LLM judge whose ratings we validate against human judgments and against an independent-family judge. Applying these benchmarks under each regime, we find the open-versus-proprietary gap is small and cheaply closed by fine-tuning. Therefore, we train UTE-1, which is a state-of-the-art text embedder among open models for Uzbek. We also demonstrate that closing the performance gap via fine-tuning is both impractical due to the intensive hardware demands of long-context legal Q\&A and unnecessary, given that legal acts change frequently. We support this by reporting a negative result from a QLoRA experiment. We distill practical guidance for similar deployments, drawn from a system serving real users in production. We release our benchmarks, evaluation code and the fine-tuned embedder (UTE-1) https://metric-ai-lab.github.io/Uzbek-Legal-RAG/{at this https URL} to support future work on low-resource legal NLP.

Coding agents repeatedly search, navigate, and retain context from evolving repositories, but disconnected indexes, language servers, and task-local histories force repeated discovery and obscure lifecycle costs. CodeNib builds reusable lexical, dense, and structural views per repository commit, maps outputs to repository-relative source ranges, maintains selected views across edits, and serves ranked search, symbol navigation, and bounded context through one runtime. Across 100 snapshots, we map quality-cost frontiers across the repository-context lifecycle. When outputs match an independent rebuild, graph and vector updates are 8.7times and 25.4times faster at the median. On the static-navigation subset matching normalized live-server locations (63% of 1,000 requests), the median per-request live/static latency ratio is 4.7times. Across five models, selected context policies preserve localization with 50--87% fewer trajectory tokens than paired grep/read. Together, these results support multi-view repository-context serving with explicit, operation-specific validity boundaries.

Practical large language model (LLM) services may involve a long system prompt, which specifies the instructions, examples, and knowledge documents of the task and is reused across numerous requests. However, the long system prompt causes throughput/latency bottlenecks as the cost of generating the next token grows w.r.t. the sequence length. This paper aims to improve the efficiency of LLM services that involve long system prompts. Our key observation is that handling these system prompts requires heavily redundant memory accesses in existing causal attention computation algorithms. Specifically, for batched requests, the cached hidden states (i.e., key-value pairs) of system prompts are transferred from off-chip DRAM to on-chip SRAM multiple times, each corresponding to an individual request. To eliminate such a redundancy, we propose RelayAttention, an attention algorithm that allows reading these hidden states from DRAM exactly once for a batch of input tokens. RelayAttention is a free lunch: it maintains the generation quality while requiring no model retraining, as it is based on a mathematical reformulation of causal attention.