Daily Papers

LLM pruning must preserve quality while meeting hardware- and workload-specific constraints on latency, throughput, and memory. Existing pruning workflows often target parameter counts, requiring practitioners to manually select model sizes that meet latency, throughput, and GPU memory limits. However, parameter count alone does not predict these metrics, which depend on the model architecture, workload, hardware, and serving engine. We introduce AutoCompress, a hardware-guided compression framework that directly incorporates such constraints into differentiable architecture search. AutoCompress jointly optimizes global and per-layer structure to produce heterogeneous architectures, guided by serving-engine cost models validated against end-to-end latency, throughput, and memory measurements. We evaluate AutoCompress on long-context local coding, batched datacenter serving, and latency-sensitive in-game interaction. Compared to the state-of-the-art Minitron pruning framework, AutoCompress improves average accuracy across eight benchmarks by 6.57, 2.35, and 0.57 percentage points on RTX 5070, RTX 5080, and H100, respectively. AutoCompress also compresses Nemotron 3.5 Super from 120B to 74B parameters for single-B200 BF16 serving at 128K context, retaining 95% of its mean benchmark score.

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.

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.

Host-resident layer streaming enables full-parameter LLM fine-tuning beyond GPU memory, but data-parallel ranks compete for shared host resources. Replicated transfers amplify traffic, while strong scaling can expose host work as computation windows shrink. We present SlideDP, a synchronous data-parallel runtime for shared-host multi-GPU systems. It maintains one authoritative host state, decouples communication routes from state layout, and pipelines parameter delivery, gradient aggregation, and CPU updates across ranks and chunks. An analytical step-time model characterizes resource bottlenecks and pipeline exposure; runtime measurements guide communication, chunking, and activation policies under a GPU memory budget. In matched-batch sweeps, SlideDP achieves geometric-mean throughput ratios of 1.46-2.64times over SlideFormer, MegaTrain, and ZeRO-Offload. On four H100s, SlideDP approaches GPU-resident FSDP2 throughput for Qwen3-14B at a smaller batch size. With a larger batch, it processes over 1M tokens per step and exceeds FSDP2's measured peak throughput by 11.2%. Separately, it supports 256K-token sequences for the same model and fine-tunes Qwen2.5-72B on four RTX 4090 GPUs. Project page: https://github.com/RegiaYoung/SlideDP.

Dynamic layer skipping reduces LLM computation by allowing each token to execute only a subset of the model's layers. However, existing skippers rely on specialized generation loops and do not integrate with modern serving engines. As a result, fewer executed layers do not necessarily translate into lower serving latency: FlexiDepth skips 8 of Llama-3-8B's 32 layers on average, yet its standard generation loop decodes 14.6--21.0% more slowly than the base model. We present vSkipper, a virtualization layer that makes dynamic layer skippers pluggable in serving engines while preserving continuous batching, fixed-shape batches, paged KV caching, and captured decode graphs. At each routed layer, vSkipper groups tokens by the skipper's decision and uses routed execution only when predicted to be profitable. We implement vSkipper in SGLang and evaluate the released FlexiDepth checkpoint against upstream SGLang under identical prompts, arrivals, output lengths, and launch settings. At the knee of upstream's load curve, vSkipper reduces mean end-to-end latency by 36.8% on GSM8K and 13.6% on BBH. Under saturation, it increases request throughput by 11.3% and 7.4%. Serving adds no statistically resolved quality loss beyond the checkpoint's own. Across synthetic skip policies, two Qwen3 skippers, and three GPUs, we demonstrate reuse without workload-specific tuning. To our knowledge, vSkipper is the first system to realize serving-efficiency gains from per-token interior layer skipping within a modern LLM serving engine. The code is open-sourced as an SGLang fork at https://github.com/AKafakA/sglang-vskipper/tree/vskipper-ref

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.

Cloud platforms are increasingly relied upon to host diverse, resource-intensive workloads due to their scalability, flexibility, and cost-efficiency. In multi-tenant cloud environments, virtual machines are consolidated on shared physical servers to improve resource utilization. While virtualization guarantees resource partitioning for CPU, memory, and storage, it cannot ensure performance isolation. Competition for shared resources such as last-level cache, memory bandwidth, and network interfaces often leads to severe performance degradation. Existing management techniques, including VM scheduling and resource provisioning, require accurate performance prediction to mitigate interference. However, this remains challenging in public clouds due to the black-box nature of VMs and the highly dynamic nature of workloads. To address these limitations, we propose CloudFormer, a dual-branch Transformer-based model designed to predict VM performance degradation in black-box environments. CloudFormer jointly models temporal dynamics and system-level interactions, leveraging 206 system metrics at one-second resolution across both static and dynamic scenarios. This design enables the model to capture transient interference effects and adapt to varying workload conditions without scenario-specific tuning. Complementing the methodology, we provide a fine-grained dataset that significantly expands the temporal resolution and metric diversity compared to existing benchmarks. Experimental results demonstrate that CloudFormer consistently outperforms state-of-the-art baselines across multiple evaluation metrics, achieving robust generalization across diverse and previously unseen workloads. Notably, CloudFormer attains a mean absolute error (MAE) of just 7.8%, representing a substantial improvement in predictive accuracy and outperforming existing methods at least by 28%.

Heterogeneous LLM serving stacks split scheduling into two layers that optimize in isolation: model routers pick a model from quality and cost signals while ignoring instance load, and serving load balancers optimize queues while ignoring quality. We present RouteBalance, a serving-aware scheduling layer that fuses both into a single online assignment over concrete model instances, jointly trading off quality, latency, and cost. A batched in-process predictor stack and dead-reckoned instance state keep the joint decision cheap on the request hot path (approx32 ms at 12 req/s). On a 13-instance, 28-GPU heterogeneous cluster serving four model sizes, a single deployed RouteBalance stack traces the upper region of the three-way quality-cost-throughput frontier. Sweeping one weight vector reaches both the highest routing-decision quality (DeepEval 0.419, +0.013 over the strongest baseline, 95% CI [{+}0.005,{+}0.022]; the ordering holds when a second judge re-scores the actually served text) and, at its cost-priority corner, per-request cost that ties the cheapest baseline. With router engineering equalized against concurrent-scoring baseline variants we build, its balanced preset serves at 2.8 s and 30 req/s, leading 2.6 to 4.1times ahead of enhanced BEST-Route at high load. (Deploying those routers as published, one serial scoring call per request, makes them collapse 23times under load, a deployment-architecture effect we isolate separately, not the routing result.) A four-arm isolation shows the benefit follows from pricing latency at model-selection time; the learned predictors contribute calibration and SLO headroom rather than the headline frontier. Code: https://github.com/AKafakA/route-balance

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

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

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.

Each LLM serving request goes through two phases. The first is prefill which processes the entire input prompt to produce one output token and the second is decode which generates the rest of output tokens, one-at-a-time. Prefill iterations have high latency but saturate GPU compute due to parallel processing of the input prompt. In contrast, decode iterations have low latency but also low compute utilization because a decode iteration processes only a single token per request. This makes batching highly effective for decodes and consequently for overall throughput. However, batching multiple requests leads to an interleaving of prefill and decode iterations which makes it challenging to achieve both high throughput and low latency. We introduce an efficient LLM inference scheduler Sarathi-Serve inspired by the techniques we originally proposed for optimizing throughput in Sarathi. Sarathi-Serve leverages chunked-prefills from Sarathi to create stall-free schedules that can add new requests in a batch without pausing ongoing decodes. Stall-free scheduling unlocks the opportunity to improve throughput with large batch sizes while minimizing the effect of batching on latency. Our evaluation shows that Sarathi-Serve improves serving throughput within desired latency SLOs of Mistral-7B by up to 2.6x on a single A100 GPU and up to 6.9x for Falcon-180B on 8 A100 GPUs over Orca and vLLM.

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.

This paper introduces Dodoor, an efficient randomized decentralized scheduler designed for task scheduling in modern data centers. Dodoor leverages advanced research on the weighted balls-into-bins model with b-batched setting. Unlike other decentralized schedulers that rely on real-time probing of remote servers, Dodoor makes scheduling decisions based on cached server information, which is updated in batches, to reduce communication overheads. To schedule tasks with dynamic, multidimensional resource requirements in heterogeneous cluster, Dodoor uses a novel load score to measure servers' loads for each scheduled task. This score captures the anti-affinity between servers and tasks in contrast to the commonly used heuristic of counting pending tasks to balance load. On a 101-node heterogeneous cluster, Dodoor is evaluated using two workloads: (i) simulated Azure virtual machines placements and (ii) real serverless Python functions executions in Docker. The evaluation shows that Dodoor reduces scheduling messages by 55--66% on both workloads. Dodoor can also increase throughput by up to 33.2% and 21.5%, reduce mean makespan latency by 12.1% and 7.2%, and improve tail latency by 21.9% and 24.6% across the two workloads.

Serverless computing has emerged as a compelling new paradigm of cloud computing models in recent years. It promises the user services at large scale and low cost while eliminating the need for infrastructure management. On cloud provider side, flexible resource management is required to meet fluctuating demand. It can be enabled through automated provisioning and deprovisioning of resources. A common approach among both commercial and open source serverless computing platforms is workload-based auto-scaling, where a designated algorithm scales instances according to the number of incoming requests. In the recently evolving serverless framework Knative a request-based policy is proposed, where the algorithm scales resources by a configured maximum number of requests that can be processed in parallel per instance, the so-called concurrency. As we show in a baseline experiment, this predefined concurrency level can strongly influence the performance of a serverless application. However, identifying the concurrency configuration that yields the highest possible quality of service is a challenging task due to various factors, e.g. varying workload and complex infrastructure characteristics, influencing throughput and latency. While there has been considerable research into intelligent techniques for optimizing auto-scaling for virtual machine provisioning, this topic has not yet been discussed in the area of serverless computing. For this reason, we investigate the applicability of a reinforcement learning approach, which has been proven on dynamic virtual machine provisioning, to request-based auto-scaling in a serverless framework. Our results show that within a limited number of iterations our proposed model learns an effective scaling policy per workload, improving the performance compared to the default auto-scaling configuration.

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.

We present Cascadia, a system for serving large language models on fleets of commodity Intel AIPCs using their CPU, integrated-GPU, and NPU resources. Every node embeds ingress, scheduling, and execution; inference requests require no dedicated routing control plane. Nodes join a libp2p QUIC mesh using CA-issued ed25519 admission certificates, gossip signed capabilities, exchange live load over direct peer streams, and route OpenAI-compatible requests to eligible peers. An operator-run certificate authority handles admission and fleet management outside the inference path. Three serving modes share one interface: whole-model execution on one node, load-balanced replicas, and pipeline-sharded chains using the compilation and speculative decoding mechanism of our companion paper. Optional KV-cache mobility reuses compatible conversation prefixes after a routing move, with cold recomputation on a miss. Signed response receipts and hash-chained logs support provenance and audit. A three-node Phi-3.5-mini NPU testbed delivered 3.10x the response throughput of its one-node configuration under ten concurrent requests; a separate four-node deployment recorded 4.06x the throughput of direct single-node serving. Paired latency observations, runtime measurements, and internal functional checks characterize the tested configurations. We compare Cascadia with IBM, Nutanix, VMware, and HPE platforms on deployment footprint, hardware requirements, scheduling, scaling, licensing, and trust, using vendor documentation. The paper repository provides benchmark scripts, curated measurements, and a claim-to-evidence map.

Offline batch inference, which leverages the flexibility of request batching to achieve higher throughput and lower costs, is becoming more popular for latency-insensitive applications. Meanwhile, recent progress in model capability and modality makes requests more diverse in compute and memory demands, creating unique opportunities for throughput improvement by resource overlapping. However, a request schedule that maximizes resource overlapping can conflict with the schedule that maximizes prefix sharing, a widely-used performance optimization, causing sub-optimal inference throughput. We present BlendServe, a system that maximizes resource utilization of offline batch inference by combining the benefits of resource overlapping and prefix sharing using a resource-aware prefix tree. BlendServe exploits the relaxed latency requirements in offline batch inference to reorder and overlap requests with varied resource demands while ensuring high prefix sharing. We evaluate BlendServe on a variety of synthetic multi-modal workloads and show that it provides up to 1.44times throughput boost compared to widely-used industry standards, vLLM and SGLang.

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.

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

Distributed cloud environments hosting data-intensive applications often experience slowdowns due to network congestion, asymmetric bandwidth, and inter-node data shuffling. These factors are typically not captured by traditional host-level metrics like CPU or memory. Scheduling without accounting for these conditions can lead to poor placement decisions, longer data transfers, and suboptimal job performance. We present a network-aware job scheduler that uses supervised learning to predict the completion time of candidate jobs. Our system introduces a prediction-and-ranking mechanism that collects real-time telemetry from all nodes, uses a trained supervised model to estimate job duration per node, and ranks them to select the best placement. We evaluate the scheduler on a geo-distributed Kubernetes cluster deployed on the FABRIC testbed by running network-intensive Spark workloads. Compared to the default Kubernetes scheduler, which makes placement decisions based on current resource availability alone, our proposed supervised scheduler achieved 34-54% higher accuracy in selecting optimal nodes for job placement. The novelty of our work lies in the demonstration of supervised learning for real-time, network-aware job scheduling on a multi-site cluster.

Large Language Models (LLMs) in agentic workflows combine multi-step reasoning, tool use, and collaboration across multiple specialized agents. Existing LLM serving engines optimize individual calls in isolation, while multi-agent frameworks focus on orchestration without system-level performance planning. As a result, repeated prompts, overlapping contexts, and concurrent executions create substantial redundancy and poor GPU utilization, especially in batch analytics scenarios. We introduce Halo, a system that brings batch query processing and optimization into agentic LLM workflows. Halo represents each workflow as a structured query plan DAG and constructs a consolidated graph for batched queries that exposes shared computation. Guided by a cost model that jointly considers prefill and decode costs, cache reuse, and GPU placement, Halo performs plan-level optimization to minimize redundant execution. Its runtime integrates adaptive batching, KV-cache sharing and migration, along with compute-communication overlap to maximize hardware efficiency. Evaluation across six benchmarks shows that Halo achieves up to 18.6x speedup for batch inference and 4.7x throughput improvement under online serving, scaling to workloads of tens of thousands of queries and complex graphs. These gains are achieved without compromising output quality. By unifying query optimization with LLM serving, Halo enables efficient agentic workflows in data analytics and decision-making applications.

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.

Large-scale distributed training in production datacenters constitutes a challenging workload bottlenecked by network communication. In response, both major industry players (e.g., Ultra Ethernet Consortium) and parts of academia have surprisingly, and almost unanimously, agreed that packet spraying is necessary to improve the performance of large-scale distributed training workloads. In this paper, we challenge this prevailing belief and pose the question: How close can a singlepath transport approach an optimal multipath transport? We demonstrate that singlepath transport (from a NIC's perspective) is sufficient and can perform nearly as well as an ideal multipath transport with packet spraying, particularly in the context of distributed training in leaf-spine topologies. Our assertion is based on four key observations about workloads driven by collective communication patterns: (i) flows within a collective start almost simultaneously, (ii) flow sizes are nearly equal, (iii) the completion time of a collective is more crucial than individual flow completion times, and (iv) flows can be split upon arrival. We analytically prove that singlepath transport, using minimal flow splitting (at the application layer), is equivalent to an ideal multipath transport with packet spraying in terms of maximum congestion. Our preliminary evaluations support our claims. This paper suggests an alternative agenda for developing next-generation transport protocols tailored for large-scale distributed training.

The exploration and application of Large Language Models (LLMs) is thriving. To reduce deployment costs, continuous batching has become an essential feature in current service frameworks. The effectiveness of continuous batching relies on an accurate estimate of the memory requirements of requests. However, due to the diversity in request output lengths, existing frameworks tend to adopt aggressive or conservative schedulers, which often result in significant overestimation or underestimation of memory consumption. Consequently, they suffer from harmful request evictions or prolonged queuing times, failing to achieve satisfactory throughput under strict Service Level Agreement (SLA) guarantees (a.k.a. goodput), across various LLM application scenarios with differing input-output length distributions. To address this issue, we propose a novel Past-Future scheduler that precisely estimates the peak memory resources required by the running batch via considering the historical distribution of request output lengths and calculating memory occupancy at each future time point. It adapts to applications with all types of input-output length distributions, balancing the trade-off between request queuing and harmful evictions, thereby consistently achieving better goodput. Furthermore, to validate the effectiveness of the proposed scheduler, we developed a high-performance LLM serving framework, LightLLM, that implements the Past-Future scheduler. Compared to existing aggressive or conservative schedulers, LightLLM demonstrates superior goodput, achieving up to 2-3times higher goodput than other schedulers under heavy loads. LightLLM is open source to boost the research in such direction (https://github.com/ModelTC/lightllm).

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.

Many LLM tasks are performed in large batches or even offline, and the performance indictor for which is throughput. These tasks usually show the characteristic of prefix sharing, where different prompt input can partially show the common prefix. However, the existing LLM inference engines tend to optimize the streaming requests and show limitations of supporting the large batched tasks with the prefix sharing characteristic. The existing solutions use the LRU-based cache to reuse the KV context of common prefix. The KV context that is about to be reused may prematurely be evicted with the implicit cache management. Even if not evicted, the lifetime of the shared KV context is extended since requests sharing the same context are not scheduled together, resulting in larger memory usage. These streaming oriented systems schedule the requests in the first-come-first-serve or similar order. As a result, the requests with larger ratio of decoding steps may be scheduled too late to be able to mix with the prefill chunks to increase the hardware utilization. Besides, the token and request number based batching can limit the size of token-batch, which keeps the GPU from saturating for the iterations dominated by decoding tokens. We propose BatchLLM to address the above problems. BatchLLM explicitly identifies the common prefixes globally. The requests sharing the same prefix will be scheduled together to reuse the KV context the best, which also shrinks the lifetime of common KV memory. BatchLLM reorders the requests and schedules the requests with larger ratio of decoding first to better mix the decoding tokens with the latter prefill chunks and applies memory-centric token batching to enlarge the token-batch sizes, which helps to increase the GPU utilization. Extensive evaluation shows that BatchLLM outperforms vLLM by 1.1x to 2x on a set of microbenchmarks and two typical industry workloads.

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.

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.

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.

Modern Intel AI PCs ship capable integrated GPUs and NPUs with 16+ GB of unified memory, and they spend considerable time idle. That is not enough memory to fit a large model such as a 70B-parameter LLM. We show that a handful of AIPCs, working together over an ordinary network, can serve models beyond the capability of any single one. We use pipeline parallelism: a model is split by layer into per-stage shards, each pre-compiled into an OpenVINO graph, so that every machine runs one shard and passes activations to the next. Three techniques make this fast enough to be useful. First, we recover the speed of the unsplit model: a naive per-stage export runs well below monolithic inference because it misses an OpenVINO GPU optimization, and injecting a beam_idx Gather into each shard triggers that optimization (the IndirectKVCache fusion) and brings the shards to parity. Second, we leverage speculative decoding on stateful OpenVINO models. Third, the pipeline serves several users at once by interleaving their requests across the stages, each request carrying its own cache (micro-batching). Together, a two-node Llama 3.1 8B INT4 pipeline serves two concurrent users at 1.79x the single-user throughput of the unsplit model on the same hardware, and the gap widens under simulated wide-area latency. The same design scales to a 70B model that no single fleet member can hold: a four-node deployment of Lunar Lake AI PCs on Intel Tiber Cloud serves a single user at interactive speed, with output token-for-token identical to the same four-node pipeline decoding without speculation. Code, raw benchmark logs, and reproduction scripts ship as a self-contained package at https://github.com/labscommunity/pipeline-sharded-inference-paper (in the top-level reproduction/ directory).

The post-training of Vision-Language-Action (VLA) models is essential due to the diversity of simulators, robot embodiments, and task objectives. Existing compute services, whether offered as direct accelerator rental or batch-workload submission, typically allocate an exclusive set of GPU and CPU resources to a single tenant. While this paradigm maximizes client flexibility, it burdens users with infrastructure adaptation, and the fixed card-hour accounting model renders short or bursty workloads both expensive for tenants and inefficient for the service provider. To address these challenges, we present JoyNexus, a unified service for multi-tenant VLA supervised fine-tuning, reinforcement learning, and evaluation. JoyNexus decouples the Training Model Service, Inference Model Service, and Environment Service, each accessed through APIs and backed by resident shared base models with tenant-specific slots. Tenants can directly invoke high-level semantic APIs for training, rollout, and evaluation, or compose custom algorithms using lower-level APIs and their assigned endpoints. Multiple tenants submit workloads concurrently; their action modules, optimizers, rollout records, and policy versions remain isolated, and the service is scheduled by the global Training Queue and Inference Queue. To further improve multi-tenant training efficiency, JoyNexus introduces group batching for heterogeneous VLA data schemas that share a compatible model-facing prefix, enabling a single shared backbone forward pass over grouped samples. Finally, we evaluate JoyNexus through workload simulation and a group-batching pipeline in a realistic embodied scenario. Results show that, compared with isolated single-tenant execution, JoyNexus reduces aggregate GPU time and improves service utilization via cross-tenant scheduling on shared resources.

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.

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.

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.

With the widespread adoption of Large Language Models (LLMs), serving LLM inference requests has become an increasingly important task, attracting active research advancements. Practical workloads play an essential role in this process: they are critical for motivating and benchmarking serving techniques and systems. However, the existing understanding of real-world LLM serving workloads is limited due to the lack of a comprehensive workload characterization. Prior analyses remain insufficient in scale and scope, thus failing to fully capture intricate workload characteristics. In this paper, we fill the gap with an in-depth characterization of LLM serving workloads collected from our worldwide cloud inference serving service, covering not only language models but also emerging multimodal and reasoning models, and unveiling important new findings in each case. Moreover, based on our findings, we propose ServeGen, a principled framework for generating realistic LLM serving workloads by composing them on a per-client basis. A practical use case in production validates that ServeGen avoids 50% under-provisioning compared to naive workload generation, demonstrating ServeGen's advantage in performance benchmarking. We will open-source ServeGen to foster future research.

Recent innovation in large language models (LLMs), and their myriad use-cases have rapidly driven up the compute capacity demand for datacenter GPUs. Several cloud providers and other enterprises have made substantial plans of growth in their datacenters to support these new workloads. One of the key bottleneck resources in datacenters is power, and given the increasing model sizes of LLMs, they are becoming increasingly power intensive. In this paper, we show that there is a significant opportunity to oversubscribe power in LLM clusters. Power oversubscription improves the power efficiency of these datacenters, allowing more deployable servers per datacenter, and reduces the deployment time, since building new datacenters is slow. We extensively characterize the power consumption patterns of a variety of LLMs and their configurations. We identify the differences between the inference and training power consumption patterns. Based on our analysis of these LLMs, we claim that the average and peak power utilization in LLM clusters for inference should not be very high. Our deductions align with the data from production LLM clusters, revealing that inference workloads offer substantial headroom for power oversubscription. However, the stringent set of telemetry and controls that GPUs offer in a virtualized environment, makes it challenging to have a reliable and robust power oversubscription mechanism. We propose POLCA, our framework for power oversubscription that is robust, reliable, and readily deployable for GPU clusters. Using open-source models to replicate the power patterns observed in production, we simulate POLCA and demonstrate that we can deploy 30% more servers in the same GPU cluster for inference, with minimal performance loss

Reusing the attention KV cache across requests is a standard way to cut prefill cost in long-context LLM serving, and production systems increasingly back the per-engine cache with a remote tier shared by every engine. We study such a tier in a disaggregated deployment of GLM-5.3, an FP8 mixture-of-experts model with multi-head latent attention (MLA), on 8xB300 nodes running prefill context parallelism (PCP8). Enabling the remote tier (LMCache with a Valkey store) left median time-to-first-token unchanged but raised the 16k-token p99 from 3.96 s to 17.3 s. Replaying a production request stream on an isolated engine, we find that a remote hit took 0.88 s against 0.31 s to recompute the prompt, and that synchronous loading turned a hit-heavy stream into an unstable queue: p99 83.32 s with the GPUs 7% busy. A two-term cost model explains both: a hit pays off only if the tier delivers more than B* = sR (2.53 GB/s for this model and GPU), and a fixed per-hit engine cost (T0 ~ 0.33 s) means that hits on prompts shorter than about 17k tokens cannot beat recompute at any bandwidth. Guided by the model, we (i) shard the MLA KV store across PCP ranks, with a proof that the existing minimum-over-ranks lookup returns the longest cached prefix and a load protocol that can never desynchronize collectives; (ii) partition the remote tier by rank, one server instance per rank with no coordination, which raises GET bandwidth 6.3x to 10.76 GB/s; (iii) add asynchronous loading to the sharded store; and (iv) fix three client bugs that caused unbounded stalls. On the hit-heavy stream, with 98.5% of prompt tokens served from the remote tier, p99 falls from 83.32 s to 0.67 s. The sharded store raises prefill throughput by 14%, and by 34% together with an upstream kernel fix. All changes are submitted upstream to LMCache.

Serving disaggregated large language models (LLMs) over tens of thousands of xPU devices (GPUs or NPUs) with reliable performance faces multiple challenges. 1) Ignoring the diversity (various prefixes and tidal requests), treating all the prompts in a mixed pool is inadequate. To facilitate the similarity per scenario and minimize the inner mismatch on P/D (prefill and decoding) processing, fine-grained organization is required, dynamically adjusting P/D ratios for better performance. 2) Due to inaccurate estimation on workload (queue status or maintained connections), the global scheduler easily incurs unnecessary timeouts in prefill. 3) Block-fixed device-to-device (D2D) KVCache transfer over cluster-level RDMA (remote direct memory access) fails to achieve desired D2D utilization as expected. To overcome previous problems, this paper proposes an end-to-end system P/D-Serve, complying with the paradigm of MLOps (machine learning operations), which models end-to-end (E2E) P/D performance and enables: 1) fine-grained P/D organization, mapping the service with RoCE (RDMA over converged ethernet) as needed, to facilitate similar processing and dynamic adjustments on P/D ratios; 2) on-demand forwarding upon rejections for idle prefill, decoupling the scheduler from regular inaccurate reports and local queues, to avoid timeouts in prefill; and 3) efficient KVCache transfer via optimized D2D access. P/D-Serve is implemented upon Ascend and MindSpore, has been deployed over tens of thousands of NPUs for more than eight months in commercial use, and further achieves 60\%, 42\% and 46\% improvements on E2E throughput, time-to-first-token (TTFT) SLO (service level objective) and D2D transfer time. As the E2E system with optimizations, P/D-Serve achieves 6.7x increase on throughput, compared with aggregated LLMs.

Data sharding, a technique for partitioning and distributing data among multiple servers or nodes, offers enhancements in the scalability, performance, and fault tolerance of extensive distributed systems. Nonetheless, this strategy introduces novel challenges, including load balancing among shards, management of node failures and data loss, and adaptation to evolving data and workload patterns. This paper proposes an innovative approach to tackle these challenges by empowering self-healing nodes with adaptive data sharding. Leveraging concepts such as self-replication, fractal regeneration, sentient data sharding, and symbiotic node clusters, our approach establishes a dynamic and resilient data sharding scheme capable of addressing diverse scenarios and meeting varied requirements. Implementation and evaluation of our approach involve a prototype system simulating a large-scale distributed database across various data sharding scenarios. Comparative analyses against existing data sharding techniques highlight the superior scalability, performance, fault tolerance, and adaptability of our approach. Additionally, the paper delves into potential applications and limitations, providing insights into the future research directions that can further advance this innovative approach.

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.

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.

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.

Modern industry-scale data centers need to manage a large number of virtual machines (VMs). Due to the continual creation and release of VMs, many small resource fragments are scattered across physical machines (PMs). To handle these fragments, data centers periodically reschedule some VMs to alternative PMs, a practice commonly referred to as VM rescheduling. Despite the increasing importance of VM rescheduling as data centers grow in size, the problem remains understudied. We first show that, unlike most combinatorial optimization tasks, the inference time of VM rescheduling algorithms significantly influences their performance, due to dynamic VM state changes during this period. This causes existing methods to scale poorly. Therefore, we develop a reinforcement learning system for VM rescheduling, VM2RL, which incorporates a set of customized techniques, such as a two-stage framework that accommodates diverse constraints and workload conditions, a feature extraction module that captures relational information specific to rescheduling, as well as a risk-seeking evaluation enabling users to optimize the trade-off between latency and accuracy. We conduct extensive experiments with data from an industry-scale data center. Our results show that VM2RL can achieve a performance comparable to the optimal solution but with a running time of seconds. Code and datasets are open-sourced: https://github.com/zhykoties/VMR2L_eurosys, https://drive.google.com/drive/folders/1PfRo1cVwuhH30XhsE2Np3xqJn2GpX5qy.

In LLM serving, reusing the KV cache of prompts across requests is critical for reducing TTFT and serving costs. Cache-affinity scheduling, which co-locates requests with the same prompt prefix to maximize KV cache reuse, often conflicts with load-balancing scheduling that distributes requests evenly across compute instances. Existing schedulers fail to reconcile this trade-off as they operate within a single mapping space, typically applying cache-affinity routing to a subset of requests and load-balanced routing to the rest, without a unified solution to achieve both goals. To address this limitation, we propose DualMap, a dual-mapping scheduling strategy for distributed LLM serving that achieves both cache affinity and load balancing. Its key idea is to map each request to two candidate instances via two independent hash functions based on the request prompt, then intelligently select the better candidate based on current system states. This design increases the likelihood that requests with shared prefixes are co-located, while evenly dispersing distinct prefixes across the cluster via ``the power of two choices''. To make DualMap robust under dynamic and skewed real-world workloads, we incorporate three techniques: 1) SLO-aware request routing, which prioritizes cache affinity but switches to load-aware scheduling when TTFT exceeds the SLO, enhancing load balance without sacrificing cache reuse; 2) hotspot-aware rebalancing, which dynamically migrates requests from overloaded to underloaded instances, mitigating hotspots and rebalancing the system; 3) lightweight dual-hash-ring scaling, which leverages a dual-hash-ring mapping to support fast and low-overhead instance scaling without costly global remapping. Experiments on real-world workloads show that DualMap improves effective request capacity by up to 2.25times under the same TTFT SLO constraints compared with SOTA work.

Enterprise data lakes often suffer from substantial amounts of duplicate and redundant data, with data volumes ranging from terabytes to petabytes. This leads to both increased storage costs and unnecessarily high maintenance costs for these datasets. In this work, we focus on identifying and reducing redundancy in enterprise data lakes by addressing the problem of 'dataset containment'. To the best of our knowledge, this is one of the first works that addresses table-level containment at a large scale. We propose R2D2: a three-step hierarchical pipeline that efficiently identifies almost all instances of containment by progressively reducing the search space in the data lake. It first builds (i) a schema containment graph, followed by (ii) statistical min-max pruning, and finally, (iii) content level pruning. We further propose minimizing the total storage and access costs by optimally identifying redundant datasets that can be deleted (and reconstructed on demand) while respecting latency constraints. We implement our system on Azure Databricks clusters using Apache Spark for enterprise data stored in ADLS Gen2, and on AWS clusters for open-source data. In contrast to existing modified baselines that are inaccurate or take several days to run, our pipeline can process an enterprise customer data lake at the TB scale in approximately 5 hours with high accuracy. We present theoretical results as well as extensive empirical validation on both enterprise (scale of TBs) and open-source datasets (scale of MBs - GBs), which showcase the effectiveness of our pipeline.

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.

Prefill-decode (PD) disaggregation has become the standard architecture for large-scale LLM serving, but in practice its deployment boundary is still determined by KVCache transfer. In conventional dense-attention models, prefill generates huge KVCache traffics that keep prefill and decode tightly coupled within a single high-bandwidth network domain, limiting heterogeneous deployment and resource elasticity. Recent hybrid-attention architectures substantially reduce KVCache size, making cross-cluster KVCache transport increasingly plausible. However, smaller KVCache alone does not make heterogeneous cross-datacenter PD serving practical: real workloads remain bursty, request lengths are highly skewed, prefix caches are unevenly distributed, and inter-cluster bandwidth fluctuates. A naive design that fully externalizes prefill can therefore still suffer from congestion, unstable queueing, and poor utilization. We present Prefill-as-a-Service (PrfaaS), a cross-datacenter serving architecture that selectively offloads long-context prefill to standalone, compute-dense prefill clusters and transfers the resulting KVCache over commodity Ethernet to local PD clusters for decode. Rather than treating reduced KVCache as sufficient, PrfaaS combines model-side KV efficiency with system-side selective offloading, bandwidth-aware scheduling, and cache-aware request placement. This design removes the requirement that heterogeneous accelerators share the same low-latency RDMA fabric, enabling independent scaling of prefill and decode capacity across loosely coupled clusters. In a case study using an internal 1T-parameter hybrid model, a PrfaaS-augmented heterogeneous deployment achieves 54% higher serving throughput and 64% lower P90 TTFT than a homogeneous PD baseline, with approximately 15% throughput gain at equal cost, while consuming only modest cross-datacenter bandwidth.

Concurrent local LLM serving on unified-memory desktops must preserve memory headroom and output fidelity, which speed-only rankings overlook. We introduce SiliconBench, which evaluates nine Apple Silicon serving engines through three lenses: speed, memory, and fidelity. We evaluate chat and agent serving on Qwen3, Qwen3.5, and Gemma 4. We use a classification task to check for quality regressions against an NVIDIA reference. DGX Spark provides a complementary serving-performance reference. Three desiderata guide interpretation: serving architecture readiness, memory discipline, and multi-node scaling. On Qwen3-0.6B, vllm-metal alone more than doubles throughput on both workloads from concurrency 1 to 16. CUDA vLLM and SGLang show stronger concurrency scaling on the same prompts. Explicit memory budgets do not guarantee memory headroom: two stacks complete every request while memory use approaches physical capacity and throughput declines. The newer model architectures have narrower engine support. Their evaluated implementations match the fidelity reference. Only three stacks satisfy the completion, fidelity, and model-coverage gates. Comparisons on larger dense and MoE models reinforce the importance of scheduling prompt processing alongside ongoing generation: vllm-metal's packed prefill-decode path maintains lower first-token latency than omlx under concurrent load. In the tested two-machine configurations, tensor parallelism over Thunderbolt RDMA scales while pipeline parallelism over TCP regresses. We release benchmark code, per-run results, and maintenance journals, supported by a workflow combining bounded agent fixes with human review.

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.

Large Language Models (LLMs) present a critical trade-off between inference quality and computational cost: larger models offer superior capabilities but incur significant latency, while smaller models are faster but less powerful. Existing serving strategies often employ fixed model scales or static two-stage speculative decoding, failing to dynamically adapt to the varying complexities of user requests or fluctuations in system performance. This paper introduces , a novel framework that reimagines LLM inference as an adaptive routing problem solved through multi-level speculative decoding. dynamically constructs and optimizes inference "paths" (chains of models) based on real-time feedback, addressing the limitations of static approaches. Our contributions are threefold: (1) An adaptive model chain scheduling mechanism that leverages performance profiling (execution times) and predictive similarity metrics (derived from token distribution divergence) to continuously select the optimal sequence of draft and verifier models, minimizing predicted latency per generated token. (2) A multi-level collaborative verification framework where intermediate models within the selected chain can validate speculative tokens, reducing the verification burden on the final, most powerful target model. (3) A synchronized state management system providing efficient, consistent KV cache handling across heterogeneous models in the chain, including precise, low-overhead rollbacks tailored for asynchronous batch processing inherent in multi-level speculation. Preliminary experiments demonstrate the validity of our method.

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.

This paper introduces DeepFlow, a scalable and serverless AI platform designed to efficiently serve large language models (LLMs) at scale in cloud environments. DeepFlow addresses key challenges such as resource allocation, serving efficiency, and cold start latencies through four main design components. First, it uses a simple serverless abstraction called the request-job-task model, which helps manage AI workloads across post-training and model serving tasks. Second, it builds an in-house serving engine FlowServe using a microkernel-inspired design, NPU-centric execution, and SPMD-based parallelism to optimize LLM serving. The system also includes novel scheduling policies tailored for both PD-disaggregated and PD-colocated configurations. With optimizations like pre-warmed pods, DRAM pre-loading, and NPU-fork, DeepFlow can scale up to 64 instances in seconds. DeepFlow has been in production for over a year, operating on a large Ascend NPU cluster and providing industrystandard APIs for fine-tuning, agent serving, and model serving to our customers.

Intelligent scaling of microservices in cloud platforms is crucial for mitigating escalating compute costs while avoiding service disruptions. Current solutions are limited to the univariate space, typically focusing on CPU usage alone to drive scaling decisions. Moreover, they address the problem as a purely forecasting task, focusing on prediction precision while neglecting the greater risks of underestimation and delays in system responsiveness. Alternative solutions are computationally complex, making them impractical for large-scale, real-time deployments. To address these challenges, we present STARIXNet, a lightweight neural network that guides resource allocation decisions in the multivariate space by capturing spatio-temporal relationships among multiple system metrics. STARIXNet models multiple quasi-dependent attributes, in particular the (S)easonal, (T)emporal, (A)uto-(R)egressive (I)ntegrated, and e(X)ogenous patterns, then implements an aggregation policy to finalize scaling decisions, prioritizing service stability, followed by cost-efficiency, over raw forecast accuracy. We empirically demonstrate the performance of STARIXNet by benchmarking against existing solutions in real-world settings. STARIXNet is deployed for critical production microservices at Walmart achieving tangible savings ranging from 10\% to 50\%, in addition to intangible benefits through improved service stability and customer experience.

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.

Large language models have been widely adopted across different tasks, but their auto-regressive generation nature often leads to inefficient resource utilization during inference. While batching is commonly used to increase throughput, performance gains plateau beyond a certain batch size, especially with smaller models, a phenomenon that existing literature typically explains as a shift to the compute-bound regime. In this paper, through an in-depth GPU-level analysis, we reveal that large-batch inference remains memory-bound, with most GPU compute capabilities underutilized due to DRAM bandwidth saturation as the primary bottleneck. To address this, we propose a Batching Configuration Advisor (BCA) that optimizes memory allocation, reducing GPU memory requirements with minimal impact on throughput. The freed memory and underutilized GPU compute capabilities can then be leveraged by concurrent workloads. Specifically, we use model replication to improve serving throughput and GPU utilization. Our findings challenge conventional assumptions about LLM inference, offering new insights and practical strategies for improving resource utilization, particularly for smaller language models.

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 language models (LLMs) propel the prosperity of interactive AI applications showcased by ChatGPT that demand timely response of inference services. However, LLM inference is computation intensive and memory intensive, and improper parameter configuration at LLM platforms may exacerbate the inference time. In this paper, we analyze the impact of LLM output token distribution on the inference queueing delay, where the max-token clipping and the batched inference are considered. By formulating an M/G/1 model, we observe that enforcing a maximum output token limit on a very small fraction of inference requests can significantly reduce the queueing delay, and our model facilitates the selection of the optimal limit. For the batch inference, we model the service process as a bulk queue in which the batch processing time is affected by the batch size and the maximum token size inside this batch jointly. The queueing delays of the batching of all buffered requests (dynamic batching), the batching of constant number of requests (fixed batching), and the batching without intra-batch waiting (elastic batching) are derived. Experimental results show that our mathematical models coincide with the event-driven simulations well.

This paper releases and analyzes a month-long trace of 85 billion user requests and 11.9 million cold starts from Huawei's serverless cloud platform. Our analysis spans workloads from five data centers. We focus on cold starts and provide a comprehensive examination of the underlying factors influencing the number and duration of cold starts. These factors include trigger types, request synchronicity, runtime languages, and function resource allocations. We investigate components of cold starts, including pod allocation time, code and dependency deployment time, and scheduling delays, and examine their relationships with runtime languages, trigger types, and resource allocation. We introduce pod utility ratio to measure the pod's useful lifetime relative to its cold start time, giving a more complete picture of cold starts, and see that some pods with long cold start times have longer useful lifetimes. Our findings reveal the complexity and multifaceted origins of the number, duration, and characteristics of cold starts, driven by differences in trigger types, runtime languages, and function resource allocations. For example, cold starts in Region 1 take up to 7 seconds, dominated by dependency deployment time and scheduling. In Region 2, cold starts take up to 3 seconds and are dominated by pod allocation time. Based on this, we identify opportunities to reduce the number and duration of cold starts using strategies for multi-region scheduling. Finally, we suggest directions for future research to address these challenges and enhance the performance of serverless cloud platforms. Our datasets and code are available here https://github.com/sir-lab/data-release

Mixture-of-Experts (MoE) models promise efficient scaling of large language models (LLMs) by activating only a small subset of experts per token, but their parallelized inference pipelines make elastic serving challenging. Existing strategies fall short: horizontal scaling provisions entire replicas of the current configuration, often tens to hundreds of accelerators, leading to coarse granularity, long provisioning delays, and costly overprovisioning. Vertical scaling offers finer adjustments but typically requires instance restarts, incurring downtime. These limitations make current approaches ill-suited for the bursty, short-lived traffic patterns common in cloud deployments. We present ElasticMoE, an elastic scaling framework for MoE LLMs that achieves fine-grained, low-latency, and zero-downtime scaling. ElasticMoE decouples inference execution from memory operations, enabling scaling steps to proceed concurrently with serving. An HBM Management Module (HMM) reuses weights and KV caches via zero-copy remapping, while high-bandwidth peer-to-peer transfers bring newly added accelerators online without interrupting service. A virtual memory based expert redistribution mechanism migrates MoE experts without costly buffer reallocations, reducing peak memory usage during expert parallelism reconfiguration. Our evaluation on Ascend NPUs with three popular MoE LLMs shows that ElasticMoE achieves up to 9x lower scale-up latency, up to 2x better throughput during scaling, and significantly improves SLO attainment compared to baselines. By enabling fine-grained, concurrent scaling with minimal disruption, ElasticMoE advances the practicality of deploying massive MoE LLMs in dynamic cloud environments.

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.

Major open-source serving stacks reuse the key-value tensors of a shared prefix by default. We measure what this prefix reuse costs in reproducibility. Holding model, decoding, seed and request order fixed at batch size one, we ran an eighty-episode multi-turn agentic tool-use workload with prefix reuse on and off across two engines and four weight formats. Without prefix reuse, repeated runs reproduced every token and log-probability in all ten configurations. With it, cache-hit and recompute paths diverged on both engines. On llama.cpp with GGUF weights this path divergence rises with quantization: for Qwen2.5-7B over ten independent server histories, it reached 37.4 percent of episodes at 16-bit and 82.5 percent at four-bit. Near-tie decisions became only about 1.2 times as common, while the cache-path change in top-two margins grew 4.9-fold from 16-bit to three-bit. Serving four-bit weights through 16-bit kernels left divergence not detectably different from 16-bit, placing the amplification mainly in the quantized execution path. At Q4_K_M, run-to-run divergence came mainly from llama.cpp's server-level prompt cache: under the canonical episode order it moved divergence by 37.5 points, and at its default, divergence spanned 20.0 to 28.7 percent under five random orders. With cache state restored, each path reproduced exactly while the two still differed. In the tested stacks, cached serving is irreproducible because the cache state is absent from the request and not reset by default. A single-turn bridge shows path divergence reaching task outcomes with no detectable net change in accuracy. We release the harness, logs, and analysis pipeline.

Serving Large Language Models (LLMs) in production faces significant challenges from highly variable request patterns and severe resource fragmentation in serverless clusters. Current systems rely on static pipeline configurations that struggle to adapt to dynamic workload conditions, leading to substantial inefficiencies. We present FlexPipe, a novel system that dynamically reconfigures pipeline architectures during runtime to address these fundamental limitations. FlexPipe decomposes models into fine-grained stages and intelligently adjusts pipeline granularity based on real-time request pattern analysis, implementing three key innovations: fine-grained model partitioning with preserved computational graph constraints, inflight pipeline refactoring with consistent cache transitions, and topology-aware resource allocation that navigates GPU fragmentation. Comprehensive evaluation on an 82-GPU cluster demonstrates that FlexPipe achieves up to 8.5x better resource efficiency while maintaining 38.3% lower latency compared to state-of-the-art systems, reducing GPU reservation requirements from 75% to 30% of peak capacity.

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.

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.

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.

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

Conventional transformer inference engines are request-driven, paying an O(n) prefill cost on every query. In streaming workloads, where data arrives continuously and queries probe an ever-growing context, this cost is prohibitive. We introduce a data-driven computational model centred on stateful sessions: a persistent KV cache advanced incrementally as new data arrives, so prefill is moved off the critical path and query latency becomes O(|q|), independent of accumulated context size. Building on this, Flash Queries reclaim idle GPU cycles between data arrivals to pre-evaluate registered questions and return cached answers before the user asks, a pattern that is structurally impossible in stateless engines because they discard intermediate state between requests. A multi-tenant continuous-batching scheduler with cell-budget admission and prefix-aware grouped prefill lets dozens of stateful sessions coexist on a single GPU while preserving full quadratic self-attention. On streaming market-data benchmarks the reference implementation achieves up to 5.9x speedup over conventional inference engines (vLLM, SGLang, TensorRT-LLM, llama.cpp), holding query latency constant as accumulated context grows.

This paper presents a novel approach to categorization of modern workload schedulers. We provide descriptions of three classes of schedulers: Operating Systems Process Schedulers, Cluster Systems Jobs Schedulers and Big Data Schedulers. We describe their evolution from early adoptions to modern implementations, considering both the use and features of algorithms. In summary, we discuss differences between all presented classes of schedulers and discuss their chronological development. In conclusion we highlight similarities in the focus of scheduling strategies design, applicable to both local and distributed systems.

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 Models (LLMs) are increasingly deployed in both latency-sensitive online services and cost-sensitive offline workloads. Co-locating these workloads on shared serving instances can improve resource utilization, but directly applying this approach to Prefill/Decode (P/D) disaggregated systems introduces severe load imbalance, as fluctuating request mixes alter the intrinsic P/D ratio. Existing dynamic adjustment techniques cannot keep up with the bursty traffic patterns of online services. We propose a latency-constraint disaggregated architecture, which separates cluster resources into latency-strict and latency-relaxed pools based on task latency requirements. This design enables flexible placement of offline decode tasks, mitigating P/D imbalance while preserving online performance. To fully exploit this flexibility, we propose (1) a bottleneck-based scheduler guided by a Roofline-based performance model for performance bottleneck based scheduling, and (2) a fast preemption mechanism that strictly enforces Service Level Objectives (SLOs) for online requests. Experiments on real-world traces show that compared to existing offline system approaches, our method improves offline throughput by up to 3x, while maintaining online request SLOs.

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.

AI agents are increasingly deployed in multi-tenant cloud environments, where they execute diverse tool calls within sandboxed containers, each call with distinct resource demands and rapid fluctuations. We present a systematic characterization of OS-level resource dynamics in sandboxed AI coding agents, analyzing 144 software engineering tasks from the SWE-rebench benchmark across two LLM models. Our measurements reveal that (1) OS-level execution (tool calls, container and agent initialization) accounts for 56-74% of end-to-end task latency; (2) memory, not CPU, is the concurrency bottleneck; (3) memory spikes are tool-call-driven with a up to 15.4x peak-to-average ratio; and (4) resource demands are highly unpredictable across tasks, runs, and models. Comparing these characteristics against serverless, microservice, and batch workloads, we identify three mismatches in existing resource controls: a granularity mismatch (container-level policies vs. tool-call-level dynamics), a responsiveness mismatch (user-space reaction vs. sub-second unpredictable bursts), and an adaptability mismatch (history-based prediction vs. non-deterministic stateful execution). We propose AgentCgroup, an intent-driven eBPF-based resource controller that exploits agents ability to declare resource needs and reconstruct execution strategies, using hierarchical cgroup structures aligned with tool-call boundaries, in-kernel enforcement via sched_ext and memcg_bpf_ops, and runtime-adaptive policies. Preliminary evaluation demonstrates improved multi-tenant isolation and reduced resource waste. AgentCgroup is open-source at https://github.com/eunomia-bpf/agentcgroup

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.

Apache Spark is a widely adopted framework for large-scale data processing. However, in industrial analytics environments, Spark's built-in schedulers, such as FIFO and fair scheduling, struggle to maintain both user-level fairness and low mean response time, particularly in long-running shared applications. Existing solutions typically focus on job-level fairness which unintentionally favors users who submit more jobs. Although Spark offers a built-in fair scheduler, it lacks adaptability to dynamic user workloads and may degrade overall job performance. We present the User Weighted Fair Queuing (UWFQ) scheduler, designed to minimize job response times while ensuring equitable resource distribution across users and their respective jobs. UWFQ simulates a virtual fair queuing system and schedules jobs based on their estimated finish times under a bounded fairness model. To further address task skew and reduce priority inversions, which are common in Spark workloads, we introduce runtime partitioning, a method that dynamically refines task granularity based on expected runtime. We implement UWFQ within the Spark framework and evaluate its performance using multi-user synthetic workloads and Google cluster traces. We show that UWFQ reduces the average response time of small jobs by up to 74% compared to existing built-in Spark schedulers and to state-of-the-art fair scheduling algorithms.

With the ubiquitous use of modern large language models (LLMs) across industries, the inference serving for these models is ever expanding. Given the high compute and memory requirements of modern LLMs, more and more top-of-the-line GPUs are being deployed to serve these models. Energy availability has come to the forefront as the biggest challenge for data center expansion to serve these models. In this paper, we present the trade-offs brought up by making energy efficiency the primary goal of LLM serving under performance SLOs. We show that depending on the inputs, the model, and the service-level agreements, there are several knobs available to the LLM inference provider to use for being energy efficient. We characterize the impact of these knobs on the latency, throughput, as well as the energy. By exploring these trade-offs, we offer valuable insights into optimizing energy usage without compromising on performance, thereby paving the way for sustainable and cost-effective LLM deployment in data center environments.

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.

Recent advances in leveraging the agentic paradigm of large language models (LLMs) utilization have significantly enhanced Text-to-SQL capabilities, enabling users without specialized database expertise to query data intuitively. However, deploying these agentic LLM-based Text-to-SQL systems in production poses substantial challenges due to their inherently multi-stage workflows, stringent latency constraints, and potentially heterogeneous GPU infrastructure in enterprise environments. Current LLM serving frameworks lack effective mechanisms for handling interdependent inference tasks, dynamic latency variability, and resource heterogeneity, leading to suboptimal performance and frequent service-level objective (SLO) violations. In this paper, we introduce HEXGEN-TEXT2SQL, a novel framework designed explicitly to schedule and execute agentic multi-stage LLM-based Text-to-SQL workflows on heterogeneous GPU clusters that handle multi-tenant end-to-end queries. HEXGEN-TEXT2SQL introduce a hierarchical scheduling approach combining global workload-balanced task dispatching and local adaptive urgency-guided prioritization, guided by a systematic analysis of agentic Text-to-SQL workflows. Additionally, we propose a lightweight simulation-based method for tuning critical scheduling hyperparameters, further enhancing robustness and adaptability. Our extensive evaluation on realistic Text-to-SQL benchmarks demonstrates that HEXGEN-TEXT2SQL significantly outperforms state-of-the-art LLM serving frameworks. Specifically, HEXGEN-TEXT2SQL reduces latency deadlines by up to 1.67times (average: 1.41times) and improves system throughput by up to 1.75times (average: 1.65times) compared to vLLM under diverse, realistic workload conditions. Our code is available at https://github.com/Relaxed-System-Lab/Hexgen-Flow.

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.

Serverless computing provides automatic resource management and pay-per-use execution, but effective autoscaling remains challenging because of dynamic workloads, cold-start latency, and dependencies among functions. We present a dependency-aware autoscaling framework that integrates graph-based bottleneck identification, short-term workload forecasting, multi-model consensus, and cost-aware scaling control. Serverless applications are represented as directed dependency graphs, and structurally important functions are identified using weighted degree centrality. Resource demand is predicted using lightweight MLP, LSTM, and CNN models. Their outputs are combined through a performance-weighted probabilistic ensemble inspired by Bayesian model averaging. The controller further incorporates cold-start awareness and cost comparison to select among scale-up, scale-down, and hold actions. Experiments using real workload traces show that supervised forecasting substantially outperforms unsupervised clustering for autoscaling decision generation. The proposed ensemble achieves 99.88 percent prediction accuracy and reduces prediction error compared with representative hybrid forecasting methods. Evaluations across multiple cloud pricing models also demonstrate consistent infrastructure cost reductions while maintaining performance targets. The results show that combining dependency analysis, multi-expert forecasting, and cost-aware control provides a robust and practical solution for serverless autoscaling.

Large-scale agentic training and evaluation with large language models (LLMs) rely on isolated, stateful execution environments in which models inspect repositories, invoke tools, execute commands, and interact with task-specific services. These workloads create sandboxes in large bursts, span heterogeneous functionality and isolation requirements, retain state across long interactions, and draw from large image corpora with limited reuse. Supporting them therefore requires an elastic execution platform rather than a single sandbox runtime. This report presents DeepSeek Elastic Compute (DSec), a production sandbox platform that exposes FnCall, container, microVM, and full-VM sandbox backends through a unified SDK. DSec coordinates placement and lifecycle management across the cluster, composes environments from independently versioned layers, combines memory sharing, reclamation, and CPU scheduling for high-density execution, and loads image data on demand from Fire-Flyer File System (3FS), a cluster-wide distributed filesystem. DSec is co-designed with the reinforcement learning (RL) framework, decouples stateful rollout execution from preemptible GPU training, coordinates sandbox lifecycle with training to preserve rollout state while reclaiming idle resources, and mitigates agent misbehavior such as reward hacking. A single production-scale unit of DSec spans around 160 nodes, serving about 3 million sandboxes per day; in production, it supports over 380,000 concurrent sandboxes and sustains over 5,000 sandbox creations per second. Our evaluation and deployment experience show that these mechanisms reduce environment setup and image-distribution overhead, improve memory efficiency, and preserve latency-sensitive performance under high-density overcommit.

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.

AI agents execute tens to hundreds of chained LLM calls per task, yet GPU schedulers treat each call as independent, discarding gigabytes of intermediate state between steps and inflating end-to-end latency by 3-8x. We argue that this request-level abstraction is fundamentally mismatched to compound AI workloads, and propose a shift to program-level scheduling: treating the entire agent workflow (not individual inference calls) as the first-class schedulable unit. We present SAGA, a distributed scheduler that implements this abstraction through three mechanisms: (1) Agent Execution Graphs that capture workflow structure to predict KV cache reuse across tool-call boundaries, achieving within 1.31x of Bélády's optimal offline policy; (2) session-affinity batching with work stealing that co-locates correlated requests while maintaining global load balance; and (3) Agent Fair Share, a task-completion-time fairness metric with provable bounded-deviation guarantees. On a 64-GPU cluster serving SWE-bench coding agents and WebArena browser tasks, SAGA reduces task completion time by 1.64x (geometric mean, p < 0.001) over vLLM v0.15.1 with prefix caching and affinity routing, while improving GPU memory utilization by 1.22x and achieving 99.2% SLO attainment under multi-tenant interference. These latency gains come at a quantified cost: approximately 30% lower peak throughput than throughput-optimal batch scheduling, a tradeoff appropriate for the latency-sensitive interactive deployments that dominate compound AI usage. Our results demonstrate that workflow-aware scheduling is essential for efficient compound AI serving.

We show that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech--two vastly different languages. Because it replaces entire pipelines of hand-engineered components with neural networks, end-to-end learning allows us to handle a diverse variety of speech including noisy environments, accents and different languages. Key to our approach is our application of HPC techniques, resulting in a 7x speedup over our previous system. Because of this efficiency, experiments that previously took weeks now run in days. This enables us to iterate more quickly to identify superior architectures and algorithms. As a result, in several cases, our system is competitive with the transcription of human workers when benchmarked on standard datasets. Finally, using a technique called Batch Dispatch with GPUs in the data center, we show that our system can be inexpensively deployed in an online setting, delivering low latency when serving users at scale.

Training billion-parameter models requires distributing model states across GPUs using fully sharded data parallel (i.e., ZeRO-3). While ZeRO-3 succeeds on clusters with high-bandwidth NVLink and InfiniBand interconnects, researchers with commodity hardware face severe inter-node all-gather bottlenecks. Existing optimizations take two approaches: GPU memory caching (MiCS, ZeRO++) trades memory capacity for reduced communication, triggering out-of-memory failures on large models; host memory offloading (ZeRO-Offload, ZeRO-Infinity) extends capacity but degrades throughput due to PCIe overhead. We observe that on bandwidth-limited clusters, host memory can serve not as an overflow tier but as a fast caching layer that outperforms inter-node communication. Based on this insight, we propose FCDP, which eliminates redundant inter-node communication while preserving ZeRO-3's minimal GPU memory footprint. FCDP caches forward-pass parameters in host memory and reuses them during the backward pass via fast intra-node all-gather, reducing inter-node all-gather by 50%. For parameter-efficient fine-tuning (PEFT), FCDP selectively communicates only trainable parameters to maximize caching, reducing inter-node traffic by over 99%. In our commodity cluster setup, FCDP achieves up to 100x higher throughput than ZeRO-3 and 51x higher than ZeRO++, while maintaining ZeRO-3's maximum batch size.

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.

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.

We survey the large language model (LLM) serving area to understand the intricate dynamics between cost-efficiency and accuracy, which is magnified by the growing need for longer contextual understanding when deploying models at a massive scale. Our findings reveal that works in this space optimize along three distinct but conflicting goals: improving serving context length (C), improving serving accuracy (A), and improving serving performance (P). Drawing inspiration from the CAP theorem in databases, we propose a CAP principle for LLM serving, which suggests that any optimization can improve at most two of these three goals simultaneously. Our survey categorizes existing works within this framework. We find the definition and continuity of user-perceived measurement metrics are crucial in determining whether a goal has been met, akin to prior CAP databases in the wild. We recognize the CAP principle for LLM serving as a guiding principle, rather than a formal theorem, to inform designers of the inherent and dynamic trade-offs in serving models. As serving accuracy and performance have been extensively studied, this survey focuses on works that extend serving context length and address the resulting challenges.

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%.

Shuffle is one of the most expensive communication primitives in distributed data processing and is difficult to scale. Prior work addresses the scalability challenges of shuffle by building monolithic shuffle systems. These systems are costly to develop, and they are tightly integrated with batch processing frameworks that offer only high-level APIs such as SQL. New applications, such as ML training, require more flexibility and finer-grained interoperability with shuffle. They are often unable to leverage existing shuffle optimizations. We propose an extensible shuffle architecture. We present Exoshuffle, a library for distributed shuffle that offers competitive performance and scalability as well as greater flexibility than monolithic shuffle systems. We design an architecture that decouples the shuffle control plane from the data plane without sacrificing performance. We build Exoshuffle on Ray, a distributed futures system for data and ML applications, and demonstrate that we can: (1) rewrite previous shuffle optimizations as application-level libraries with an order of magnitude less code, (2) achieve shuffle performance and scalability competitive with monolithic shuffle systems, and break the CloudSort record as the world's most cost-efficient sorting system, and (3) enable new applications such as ML training to easily leverage scalable shuffle.

The rapid evolution of large language models (LLMs), driven by growing parameter scales, adoption of mixture-of-experts (MoE) architectures, and expanding context lengths, imposes unprecedented demands on AI infrastructure. Traditional AI clusters face limitations in compute intensity, memory bandwidth, inter-chip communication, and latency, compounded by variable workloads and strict service-level objectives. Addressing these issues requires fundamentally redesigned hardware-software integration. This paper introduces Huawei CloudMatrix, a next-generation AI datacenter architecture, realized in the production-grade CloudMatrix384 supernode. It integrates 384 Ascend 910C NPUs and 192 Kunpeng CPUs interconnected via an ultra-high-bandwidth Unified Bus (UB) network, enabling direct all-to-all communication and dynamic pooling of resources. These features optimize performance for communication-intensive operations, such as large-scale MoE expert parallelism and distributed key-value cache access. To fully leverage CloudMatrix384, we propose CloudMatrix-Infer, an advanced LLM serving solution incorporating three core innovations: a peer-to-peer serving architecture that independently scales prefill, decode, and caching; a large-scale expert parallelism strategy supporting EP320 via efficient UB-based token dispatch; and hardware-aware optimizations including specialized operators, microbatch-based pipelining, and INT8 quantization. Evaluation with the DeepSeek-R1 model shows CloudMatrix-Infer achieves state-of-the-art efficiency: prefill throughput of 6,688 tokens/s per NPU and decode throughput of 1,943 tokens/s per NPU (<50 ms TPOT). It effectively balances throughput and latency, sustaining 538 tokens/s even under stringent 15 ms latency constraints, while INT8 quantization maintains model accuracy across benchmarks.

We present the design of a new large scale orchestration layer for accelerators. Our system, Pathways, is explicitly designed to enable exploration of new systems and ML research ideas, while retaining state of the art performance for current models. Pathways uses a sharded dataflow graph of asynchronous operators that consume and produce futures, and efficiently gang-schedules heterogeneous parallel computations on thousands of accelerators while coordinating data transfers over their dedicated interconnects. Pathways makes use of a novel asynchronous distributed dataflow design that lets the control plane execute in parallel despite dependencies in the data plane. This design, with careful engineering, allows Pathways to adopt a single-controller model that makes it easier to express complex new parallelism patterns. We demonstrate that Pathways can achieve performance parity (~100% accelerator utilization) with state-of-the-art systems when running SPMD computations over 2048 TPUs, while also delivering throughput comparable to the SPMD case for Transformer models that are pipelined across 16 stages, or sharded across two islands of accelerators connected over a data center network.

Current heterogeneity-aware training systems for large models balance workloads by assigning unequal numbers of layers across pipeline stages, a strategy aimed at equalizing execution time through a unique pipeline configuration. However, this approach fails to address critical memory constraints and suffers from inherently coarse balancing granularity. In this paper, we propose Heterogeneous Pipeline Parallelism (HPP), a novel approach enabling efficient and fine-grained data balance across heterogeneous pipelines. To address HPP's key challenges, prohibitive search overhead for optimal configurations and high communication overhead from asymmetric All-Reduce, we design the ETH training system. ETH employs a hierarchical workload balance framework that jointly optimizes balance across heterogeneous pipelines and within individual pipeline stages. To mitigate asymmetric communication costs, ETH implements block-wise gradient aggregation. Furthermore, it integrates specialized optimizations that dramatically reduce HPP configuration search overhead. Evaluations demonstrate ETH achieves up to 2x training speedup while reducing configuration generation overhead by up to 56x compared to state-of-the-art systems. The code is available at https://github.com/YuMJie/ETH.

Data-residency constraints force enterprises to self-host LLMs, but continuous adoption of newer models without decommissioning their predecessors expands the serving fleet, fragmenting a finite GPU pool. We consolidate traffic from over 200 internal applications onto a single model by closing quality gaps identified through production error analysis along three axes: instruction following, function-calling, and internal task distribution. Quality is tracked by offline benchmarks stratified to production traffic and scored by deterministic verifiers or calibrated LLM judges. Rather than optimising all objectives jointly, which introduces cross-domain reward interference, we train a separate GRPO expert per axis and merge them via two-stage SLERP. Each expert's reward exposes a distinct failure mode, namely semantic collapse, over-calling, and verbosity hacking, each requiring a domain-specific fix. In non-reasoning mode the recipe surpasses a {sim}7times larger by total parameters baseline on the in-house Arena with 69.6 to 65.8, instruction following with 0.85 to 0.83, and function-calling with 0.79 to 0.77, while lifting general dialogue benchmarks. The model absorbs 50% of platform traffic, 116M requests per month, at a fraction of the serving cost.

AI-powered search products such as ChatGPT search, Google's AI Overviews, and Perplexity provide LLM-synthesized answers grounded in live web results. We developed OreoLook (formerly lixSearch), an open-source answer engine using automated browser agents and provider-routed LLM inference. Its local search, caching, session-management, and embedding stack runs on commodity CPU hardware; answer synthesis is performed by a remote inference provider. As usage grew, sessions lost context, equivalent queries triggered redundant work, and URLs were repeatedly embedded across sessions. We present a three-layer caching architecture: (1) a Session Context Window maintaining a rolling window of recent messages in Redis with automatic overflow to Huffman-compressed disk archives; (2) a Semantic Query Cache catches rephrasings via cosine similarity on embedding vectors, eliminating redundant LLM invocations; and (3) a URL Embedding Cache that deduplicates embedding computations across sessions. Deployed on a single 8-vCPU Intel Cascade Lake server (2 GHz, 32 GB RAM) running 30 Hypercorn worker processes across three containerized replicas, the evaluated system reported an 89.3% aggregate Redis keyspace hit rate with 0.1 ms read latency and just 1.38 MB of memory overhead. A background LRU eviction daemon migrates idle sessions from Redis to disk and re-hydrates them on demand, enabling conversations that can be resumed hours or days later under the configured retention policy.

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.

Lowering costs by driving high utilization across deep learning workloads is a crucial lever for cloud providers. We present Singularity, Microsoft's globally distributed scheduling service for highly-efficient and reliable execution of deep learning training and inference workloads. At the heart of Singularity is a novel, workload-aware scheduler that can transparently preempt and elastically scale deep learning workloads to drive high utilization without impacting their correctness or performance, across a global fleet of AI accelerators (e.g., GPUs, FPGAs). All jobs in Singularity are preemptable, migratable, and dynamically resizable (elastic) by default: a live job can be dynamically and transparently (a) preempted and migrated to a different set of nodes, cluster, data center or a region and resumed exactly from the point where the execution was preempted, and (b) resized (i.e., elastically scaled-up/down) on a varying set of accelerators of a given type. Our mechanisms are transparent in that they do not require the user to make any changes to their code or require using any custom libraries that may limit flexibility. Additionally, our approach significantly improves the reliability of deep learning workloads. We show that the resulting efficiency and reliability gains with Singularity are achieved with negligible impact on the steady-state performance. Finally, our design approach is agnostic of DNN architectures and handles a variety of parallelism strategies (e.g., data/pipeline/model parallelism).

Generative models are reshaping the live-streaming industry by redefining how content is created, styled, and delivered. Previous image-based streaming diffusion models have powered efficient and creative live streaming products but have hit limits on temporal consistency due to the foundation of image-based designs. Recent advances in video diffusion have markedly improved temporal consistency and sampling efficiency for offline generation. However, offline generation systems primarily optimize throughput by batching large workloads. In contrast, live online streaming operates under strict service-level objectives (SLOs): time-to-first-frame must be minimal, and every frame must meet a per-frame deadline with low jitter. Besides, scalable multi-GPU serving for real-time streams remains largely unresolved so far. To address this, we present StreamDiffusionV2, a training-free pipeline for interactive live streaming with video diffusion models. StreamDiffusionV2 integrates an SLO-aware batching scheduler and a block scheduler, together with a sink-token--guided rolling KV cache, a motion-aware noise controller, and other system-level optimizations. Moreover, we introduce a scalable pipeline orchestration that parallelizes the diffusion process across denoising steps and network layers, achieving near-linear FPS scaling without violating latency guarantees. The system scales seamlessly across heterogeneous GPU environments and supports flexible denoising steps (e.g., 1--4), enabling both ultra-low-latency and higher-quality modes. Without TensorRT or quantization, StreamDiffusionV2 renders the first frame within 0.5s and attains 58.28 FPS with a 14B-parameter model and 64.52 FPS with a 1.3B-parameter model on four H100 GPUs, making state-of-the-art generative live streaming practical and accessible--from individual creators to enterprise-scale platforms.

Simulation offers unique values for both enumeration and extrapolation purposes, and is becoming increasingly important for managing the massive machine learning (ML) clusters and large-scale distributed training jobs. In this paper, we build Echo to tackle three key challenges in large-scale training simulation: (1) tracing the runtime training workloads at each device in an ex-situ fashion so we can use a single device to obtain the actual execution graphs of 1K-GPU training, (2) accurately estimating the collective communication without high overheads of discrete-event based network simulation, and (3) accounting for the interference-induced computation slowdown from overlapping communication and computation kernels on the same device. Echo delivers on average 8% error in training step -- roughly 3x lower than state-of-the-art simulators -- for GPT-175B on a 96-GPU H800 cluster with 3D parallelism on Megatron-LM under 2 minutes.

Serving Large Language Models (LLMs) is a GPU-intensive task where traditional autoscalers fall short, particularly for modern Prefill-Decode (P/D) disaggregated architectures. This architectural shift, while powerful, introduces significant operational challenges, including inefficient use of heterogeneous hardware, network bottlenecks, and critical imbalances between prefill and decode stages. We introduce HeteroScale, a coordinated autoscaling framework that addresses the core challenges of P/D disaggregated serving. HeteroScale combines a topology-aware scheduler that adapts to heterogeneous hardware and network constraints with a novel metric-driven policy derived from the first large-scale empirical study of autoscaling signals in production. By leveraging a single, robust metric to jointly scale prefill and decode pools, HeteroScale maintains architectural balance while ensuring efficient, adaptive resource management. Deployed in a massive production environment on tens of thousands of GPUs, HeteroScale has proven its effectiveness, increasing average GPU utilization by a significant 26.6 percentage points and saving hundreds of thousands of GPU-hours daily, all while upholding stringent service level objectives.

Request scheduling is a key challenge in large-scale clusters serving agentic large language model (LLM) workloads. An effective scheduler must preserve key-value cache (KVC) reuse across long, shared prefixes, meet token-level latency service-level objectives (SLOs), and minimize GPU resource footprint. Existing schedulers struggle to reconcile these requirements: request consolidation can sacrifice cache locality and increase prefill/decode interference, compromising both SLO attainment and resource efficiency. We present PackServe, a scheduler designed to reduce resource costs while meeting latency SLOs for agentic LLM serving. PackServe uses compact white-box models to predict latency under prefill/decode interference. Guided by these predictions, it packs requests onto fewer serving instances while preserving KVC reuse and SLO constraints, trading available latency headroom for improved per-instance throughput. Evaluation on 64 NVIDIA H20 GPUs shows that PackServe uses up to 16.8% and 24.6% fewer GPU-hours than state-of-the-art schedulers under 30-ms and 50-ms TPOT targets, respectively, while meeting the target TPOT objectives. PackServe has also been deployed in our production cluster comprising over 1000 GPUs, where it reduces the resource footprint by 34.7% compared with the original production scheduler.

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.

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

Multi-agent LLM applications organize execution in synchronized rounds where a central scheduler gathers outputs from all agents and redistributes the combined context. This All-Gather communication pattern creates massive KV Cache redundancy, because every agent's prompt contains the same shared output blocks, yet existing reuse methods fail to exploit it efficiently. We present TokenDance, a system that scales the number of concurrent agents by exploiting the All-Gather pattern for collective KV Cache sharing. TokenDance's KV Collector performs KV Cache reuse over the full round in one collective step, so the cost of reusing a shared block is paid once regardless of agent count. Its Diff-Aware Storage encodes sibling caches as block-sparse diffs against a single master copy, achieving 11-17x compression on representative workloads. Evaluation on GenerativeAgents and AgentSociety shows that TokenDance supports up to 2.7x more concurrent agents than vLLM with prefix caching under SLO requirement, reduces per-agent KV Cache storage by up to 17.5x, and achieves up to 1.9x prefill speedup over per-request position-independent caching.

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI. It features a KVCache-centric disaggregated architecture that separates the prefill and decoding clusters. It also leverages the underutilized CPU, DRAM, and SSD resources of the GPU cluster to implement a disaggregated cache of KVCache. The core of Mooncake is its KVCache-centric scheduler, which balances maximizing overall effective throughput while meeting latency-related Service Level Objectives (SLOs). Unlike traditional studies that assume all requests will be processed, Mooncake faces challenges due to highly overloaded scenarios. To mitigate these, we developed a prediction-based early rejection policy. Experiments show that Mooncake excels in long-context scenarios. Compared to the baseline method, Mooncake can achieve up to a 525% increase in throughput in certain simulated scenarios while adhering to SLOs. Under real workloads, Mooncake's innovative architecture enables Kimi to handle 75% more requests.

LLM-agent services repeatedly execute small deterministic transitions between model and tool calls: route an outcome, update state, and emit the next effect. We ask when this control path exposes enough concurrent work for GPU execution, and what changes when a GPU-computed route decision remains on device. We formalize the ready-cohort boundary using fixed-partition share F, exact offline share P*, local upper bound U, and online achieved share A. Under zero service time, unlimited capacity, and equal relative launch deadlines, a specialized dynamic program computes P* exactly. In a stationary Poisson replay of one pinned 851-session public trace panel, the primary condition at 100,000 target active sessions, K=256, and a 50 ms launch deadline gives F=30.19%, P*=43.00%, and U=45.85%. Exact packing recovers 81.83% of the opportunity lost at fixed window boundaries. The outcome-derived route key is a conditioning proxy, not proof of executable identity. A separate mechanism study keeps a GPU-computed binary decision on device instead of returning four bytes to the host and redispatching. Across four named GPU placements, the device-resident path is faster in all 36 configurations; within-placement row-median ratios range from 1.19x to 2.39x. Across both admissible mechanisms, all 14,557,440 tested batched invocations match a separately implemented host oracle. A fixed nested device graph that removes no host decision is slower in all 60 configurations across five placements. Together, the studies establish two measurable gates for GPU agent control: deadline-feasible cohort supply and observation placement. A joined finite online runtime is required to measure A, CPU displacement, and service-level benefit.

Attention efficiency is critical to large language model (LLM) inference. While prior advances optimize attention execution for individual requests (e.g., FlashAttention), production LLM serving relies on batching requests with highly heterogeneous sequence lengths for high serving throughput. This mismatch induces severe computation and I/O imbalance, exacerbates stragglers, and underutilizes GPU resources. We present PackInfer, a kernel-level attention framework that enables compute- and I/O-aware execution for heterogeneous batched inference. PackInfer orchestrates batched requests into load-balanced execution groups, effectively saturating GPU utilization by packing multiple requests into unified kernel launches. By constructing attention kernels directly over packed query-key regions, PackInfer eliminates redundant computation and balances thread-block execution. It then incorporates I/O-aware grouping that co-locates shared-prefix requests and reorganizes KV caches into group-contiguous layouts, reducing memory fragmentation and redundant data movement as generation evolves. Evaluations on real-world workloads show that PackInfer reduces inference latency by 13.0-20.1%, and improves throughput by 20% compared to the state-of-the-art FlashAttention.

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.

LLM serving relies on prefix caching to improve inference performance. As growing contexts push key-value (KV) cache footprint far beyond GPU HBM and CPU DRAM capacity, KV cache is increasingly offloaded to NVMe SSDs. Unfortunately, restoring KV cache from SSDs suffers from poor I/O performance and incurs significant GPU stalls. This is primarily because the fragmented GPU memory layout results in a massive number of tiny random I/Os, rendering the low-parallelism CPU a severe bottleneck even with GPU Direct Storage (GDS), which still relies on CPU intervention to initiate each I/O and thus remains CPU-centric. This paper presents Tutti, an efficient SSD-backed KV caching solution that eliminates CPU intervention from the critical data and I/O control paths between HBM and SSDs. At the core of Tutti is a GPU-centric KV cache object store, in which the CPU is only responsible for asynchronously loading I/O kernels once per layer to the GPU. Tutti saturates NVMe SSD bandwidth and reduces GPU stalls to near zero through the following designs: (i) we provide a GPU-native object abstraction that enables bulk KV cache transfers and management; (ii) we re-architect the GPU storage stack by introducing GPU io_uring to support asynchronous GPU direct object I/O; and (iii) we propose slack-aware I/O scheduling to avoid GPU resource contention. We have implemented Tutti and integrated it to vLLM. Extensive evaluation shows that compared to the state-of-the-art GDS-enabled, SSD-backed LMCache, Tutti reduces TTFT by 78.3% under strict SLO constraints and improves the achievable request rate by 2x. The serving cost is reduced by 27%. Tutti achieves nearly the same inference performance as DRAM-backed LMCache, while providing almost infinite capacity.

Multi-turn LLM serving accumulates dialogue history whose Key-Value (KV) cache grows with every turn and every user, quickly exceeding the model weights themselves and making memory -- not compute -- the binding constraint on throughput. Non-uniform KV compression, which allocates heterogeneous budgets across attention heads, preserves accuracy far better than uniform schemes, yet remains impractical: modern serving stacks assume identical KV lengths across heads, so heterogeneity traps freed memory as page fragmentation, spends up to 25% of prefill time reclaiming scattered pages, and skews GPU workloads that inflate decode latency by up to 1.7times or burn 15--20% of each decode step on re-planning. We observe that this heterogeneity need not be discovered at runtime: head-wise retention follows a two-level structural regularity -- an input-invariant head ranking with narrowly bounded per-head ratios -- that can be calibrated offline from as few as 50 samples. Building on this insight, we present Tangram, a serving framework that statically resolves what prior systems handle dynamically: Budget Reservation fixes each head's post-compression footprint at scheduling time, eliminating page reclamation; Ragged Paging clusters similar-budget heads into independent page tables, turning fragmentation into reclaimable memory; and Ahead-of-Time Load Balancing precomputes balanced GPU partitions with zero runtime planning. Implemented on vLLM, Tangram serves as a drop-in substrate for existing non-uniform compression methods, matching their accuracy while improving end-to-end throughput by up to 2.6times over the full-KV baseline. Our implementation is publicly available at https://github.com/aiha-lab/TANGRAM.

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

As inference on Large Language Models (LLMs) emerges as an important workload in machine learning applications, weight quantization has become a standard technique for efficient GPU deployment. Quantization not only reduces model size, but has also been shown to yield substantial speedups for single-user inference, due to reduced memory movement, with low accuracy impact. Yet, it remains open whether speedups are achievable also in batched settings with multiple parallel clients, which are highly relevant for practical serving. It is unclear whether GPU kernels can be designed to remain practically memory-bound, while supporting the substantially increased compute requirements of batched workloads. This paper resolves this question positively by describing the design of Mixed-precision Auto-Regressive LINear kernels, called MARLIN. Concretely, given a model whose weights are compressed via quantization to, e.g., 4 bits per element, MARLIN shows that batchsizes up to 16-32 can be supported with close to maximum (4times) quantization speedup, and larger batchsizes up to 64-128 with gradually decreasing, but still significant, acceleration. MARLIN accomplishes this via a combination of techniques, such as asynchronous memory access, complex task scheduling and pipelining, and bespoke quantization support. Our experiments show that MARLIN's near-optimal performance on individual LLM layers across different scenarios can also lead to end-to-end LLM inference speedups (of up to 2.8times) when integrated with the popular vLLM serving engine. Finally, MARLIN is extensible to further compression techniques, like NVIDIA 2:4 sparsity, leading to additional speedups.

Software modernisation through the migration from monolithic architectures to microservices has become increasingly critical, yet identifying effective service boundaries remains a complex and unresolved challenge. Although numerous automated microservice decomposition frameworks have been proposed, their evaluation is often fragmented due to inconsistent benchmark systems, incompatible metrics, and limited reproducibility, thus hindering objective comparison. This work presents a unified comparative evaluation of state-of-the-art microservice decomposition approaches spanning static, dynamic, and hybrid techniques. Using a consistent metric computation pipeline, we assess the decomposition quality across widely used benchmark systems (JPetStore, AcmeAir, DayTrader, and Plants) using Structural Modularity (SM), Interface Number(IFN), Inter-partition Communication (ICP), Non-Extreme Distribution (NED), and related indicators. Our analysis combines results reported in prior studies with experimentally reproduced outputs from available replication packages. Findings indicate that the hierarchical clustering-based methods, particularly HDBScan, produce the most consistently balanced decompositions across benchmarks, achieving strong modularity while minimizing communication and interface overhead.

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.

The rapid proliferation of data centers (DCs), driven by cloud computing and artificial intelligence (AI), has led to massive energy demand and carbon emissions, posing significant sustainability challenges. Carbon-aware optimization in geographically distributed data centers has been widely studied. Most existing approaches mainly focus on operational carbon emissions from server usage. However, existing literature often ignores workload-induced thermal stress, which accelerates nonlinear hardware degradation. This leads to more frequent server replacements and ultimately increases embodied carbon emissions. To address these limitations, we propose a comprehensive carbon life-cycle modeling framework for distributed data centers. Apart from operational carbon emissions, this work combines workload scheduling with a utilization-dependent exponential aging model to evaluate long-term carbon costs from server degradation. In order to solve the proposed optimization model in an online and privacy-preserving manner, an enhanced Lyapunov framework with time-varying queue shifting (TVQS) is first introduced to handle system uncertainties. Then, a zero-sum perturbation-based alternating direction method of multipliers (ZSP-ADMM) framework is developed to enable distributed coordination across geographically separated data centers while protecting locally exchanged workload information. Simulation results demonstrate that the proposed approach achieves up to 13.0% lower carbon emissions and 12.6% lower operational costs compared with benchmarks.

Deep learning thrives with large neural networks and large datasets. However, larger networks and larger datasets result in longer training times that impede research and development progress. Distributed synchronous SGD offers a potential solution to this problem by dividing SGD minibatches over a pool of parallel workers. Yet to make this scheme efficient, the per-worker workload must be large, which implies nontrivial growth in the SGD minibatch size. In this paper, we empirically show that on the ImageNet dataset large minibatches cause optimization difficulties, but when these are addressed the trained networks exhibit good generalization. Specifically, we show no loss of accuracy when training with large minibatch sizes up to 8192 images. To achieve this result, we adopt a hyper-parameter-free linear scaling rule for adjusting learning rates as a function of minibatch size and develop a new warmup scheme that overcomes optimization challenges early in training. With these simple techniques, our Caffe2-based system trains ResNet-50 with a minibatch size of 8192 on 256 GPUs in one hour, while matching small minibatch accuracy. Using commodity hardware, our implementation achieves ~90% scaling efficiency when moving from 8 to 256 GPUs. Our findings enable training visual recognition models on internet-scale data with high efficiency.

Large language models (LLMs) require vast amounts of GPU compute to train, but limited availability and high costs of GPUs make homogeneous clusters impractical for many organizations. Instead, assembling heterogeneous clusters by pooling together GPUs of different generations allows them to achieve higher aggregate compute and make use of all available GPUs. However, training on heterogeneous clusters presents several challenges, including load balancing across GPUs, optimizing memory usage to accommodate varying memory capacities, and ensuring communication-efficient training over diverse network interconnects potentially spanning multiple datacenters. In this paper, we make the case that efficient training on heterogeneous clusters requires (1) the integration of pipeline parallelism and data parallelism in a manner that is both communication- and memory-efficient, and (2) a more adaptable configuration of pipeline and data parallelism, which includes the capability to flexibly partition GPUs into asymmetric pipeline parallel stages and to incorporate heterogeneous GPUs within the same data parallelism group. We propose Zorse, the first system to unify all these capabilities while incorporating a planner that automatically configures training strategies for a given workload. Our evaluation shows that Zorse significantly outperforms state-of-the-art systems in heterogeneous training scenarios.

The growing interest in artificial intelligence has created workloads that require both sequential and random access. At the same time, NVMe-backed storage solutions have emerged, providing caching capability for large columnar datasets in cloud storage. Current columnar storage libraries fall short of effectively utilizing an NVMe device's capabilities, especially when it comes to random access. Historically, this has been assumed an implicit weakness in columnar storage formats, but this has not been sufficiently explored. In this paper, we examine the effectiveness of popular columnar formats such as Apache Arrow, Apache Parquet, and Lance in both random access and full scan tasks against NVMe storage. We argue that effective encoding of a column's structure, such as the repetition and validity information, is the key to unlocking the disk's performance. We show that Parquet, when configured correctly, can achieve over 60x better random access performance than default settings. We also show that this high random access performance requires making minor trade-offs in scan performance and RAM utilization. We then describe the Lance structural encoding scheme, which alternates between two different structural encodings based on data width, and achieves better random access performance without making trade-offs in scan performance or RAM utilization.

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.