LLM Serving

LLM: Large Language Model

Overview

Large language model serving studies how to run inference efficiently for many concurrent requests, balancing response speed, throughput, cost, and service-level objectives. Common approaches include continuous batching and prefill–decode scheduling, request routing, and managing or compressing KV caches; newer systems also use disaggregated hardware, speculative decoding, and workload-aware power control. Evaluations use request traces and production-like workloads to measure time to first token, token latency, throughput, quality, and resource use across models and hardware. A central challenge is that workloads and output lengths vary, so policies that improve throughput or cost can worsen tail latency, fairness, or response quality.

Latest papers

249 papers37 papers in the last four weeks, up 23% on the four weeks before. 0.3% of all new papers.

Jan 30, 2026

VoxServe: Streaming-Centric Serving System for Speech Language Models

Speech Language Models (SpeechLMs) are increasingly deployed for streaming speech generation, where audio playback must start quickly and never stall. Serving them requires running two very different model components on the same system. An autoregressive LLM backbone emits audio tokens, and a codec converts chunks of those tokens into waveforms. Existing systems run the two as separately scheduled stages, and therefore either serialize them, let them interfere, or strand capacity by placing them on separate devices. We observe that overlapping the backbone and the codec on separate parts of the GPU raises throughput. Although this increases codec latency, most chunks can tolerate it, as long as it neither lies on the critical path of time-to-first-audio (TTFA) nor causes a playback stall. Based on this insight, we present VoxServe, a SpeechLM serving system that allocates GPU resources according to the urgency of chunks. VoxServe executes work on three asynchronous lanes. The LM lane runs the backbone on a large partition of the GPU's streaming multiprocessors, the background codec lane runs on a small partition beside it, and the urgent lane uses the whole GPU. The scheduler queues each request to the LM lane and routes every chunk the backbone completes by its urgency. A request's first chunk and chunks close to their playback deadline go to the urgent lane, and the rest are batched on the background lane. On Qwen3-TTS, VoxServe sustains 1.5x the request rate of the best existing system at a 200ms TTFA target without playback stalls. The code of VoxServe is available at https://github.com/vox-serve/vox-serve.
Jan 29, 2026

Test-Time Compute Games

Test-time compute has emerged as a promising strategy to enhance the reasoning abilities of large language models (LLMs). However, this strategy has in turn increased how much users pay cloud-based providers offering LLM-as-a-service, since providers charge users for the amount of test-time compute they use to generate an output. In our work, we show that the market of LLM-as-a-service is socially inefficient: providers have a financial incentive to increase the amount of test-time compute, even if this increase contributes little to the quality of the outputs. To address this inefficiency, we introduce a reverse second-price auction mechanism where providers bid their offered price and (expected) quality for the opportunity to serve a user, and users pay proportionally to the marginal value generated by the winning provider relative to the second-highest bidder. To illustrate and complement our theoretical results, we conduct experiments with multiple instruct models from the Llama\texttt{Llama} and Qwen\texttt{Qwen} families, as well as reasoning models distilled from DeepSeek-R1\texttt{DeepSeek-R1}, on math and science benchmark datasets.
Dec 12, 2025

xGR: Efficient Generative Recommendation Serving at Scale

Recommendation system delivers substantial economic benefits by providing personalized predictions. Generative recommendation (GR) integrates LLMs to enhance the understanding of long user-item sequences. Despite employing attention-based architectures, GR's workload differs markedly from that of LLM serving. GR typically processes long prompt while producing short, fixed-length outputs, yet the computational cost of each decode phase is especially high due to the large beam width. Furthermore, since the beam search involves a vast item space, the sorting overhead becomes particularly time-consuming. We propose xGR, a GR-oriented serving system that meets strict low-latency requirements under high-concurrency scenarios. First, xGR unifies the processing of prefill and decode phases through staged computation and separated KV cache. Second, xGR enables early sorting termination and mask-based item filtering with data structure reuse. Third, xGR reconstructs the overall pipeline to exploit multi-level overlap and multi-stream parallelism. The experiments on real-world datasets demonstrate that xGR achieves at least 2.89x throughput compared to the state-of-the-art baseline under strict latency constraints.
Oct 7, 2025

Systematic Exploration of Multi-core Architectures for Efficient LLM Serving using WaferAI-SIM

With the widespread adoption of Large Language Models (LLMs), the demand for high-performance LLM inference services continues to grow. Multi-core AI accelerators, such as Groq, Graphcore IPU, and Cerebras WSE, provide promising platforms for LLM serving, but their distributed memory systems require careful coordination between hardware configuration and serving policies. Otherwise, mismatched tensor partitioning, data placement, and memory management can substantially underutilize compute and communication resources. To address these challenges, we present WaferAI-SIM, a multi-level simulation framework that combines transaction-level simulation with an analytical performance model. WaferAI-SIM enables simulator-driven co-design of LLM serving strategies and multi-core accelerator architectures, targeting the early design stage in which emerging platforms are not yet broadly available for empirical serving studies. It captures how LLM serving policies interact with compute-core count, memory hierarchy, and interconnect topology, enabling architecture-aware exploration beyond GPU-centric assumptions. We evaluate representative LLMs across a range of chip configurations and serving scenarios. Across the evaluation, WaferAI-SIM reports 1.32×\times--6.03×\times latency improvements, where the lower endpoint comes from ring-based placement at TP=16 over the placement baselines, and the upper endpoint comes from K-dimension TP over MN-dimension TP for Qwen3_4B at TP=4 with sequence length 256. For LLM serving, our findings provide guidance for co-designing hardware architectures and serving strategies for multi-core AI accelerators across diverse LLM workloads.
Sep 25, 2025

Ranking Before Serving: Low-Latency LLM Serving via Pairwise Learning-to-Rank

Efficient scheduling of large language model (LLM) inference tasks is critical for achieving low latency and high throughput, a challenge that is becoming increasingly acute with the rise of reasoning-capable LLMs whose generation lengths are highly variable. Traditional strategies like First Come, First-Serve (FCFS) often suffer from Head-of-Line (HOL) blocking, where long-running tasks delay shorter ones queued behind them. In this paper, we introduce PARS, a prompt-aware LLM task scheduler that mitigates HOL blocking by approximating shortest-job-first (SJF) scheduling through pairwise ranking with a margin ranking loss. PARS effectively predicts response-length-based task ordering directly from prompts, thereby optimizing scheduling decisions with minimal overhead. In addition, it integrates seamlessly with vLLM, a state-of-the-art LLM serving system, for the research community. Extensive experiments across multiple LLM models and real-world inference use cases, including chat, math, and code generation, demonstrate that PARS significantly reduces latency by up to 15.7x compared to the vLLM default scheduler. Cross-model evaluations demonstrate that our design generalizes effectively, allowing effective scheduling across diverse LLMs without requiring model-specific retraining.
Sep 5, 2025

VoltanaLLM: Energy-Efficient and SLO-Aware Disaggregated LLM Serving via Adaptive Frequency Control and State-Space Routing

The energy cost of Large Language Model (LLM) inference is rapidly becoming a barrier to sustainable and scalable deployment. Although modern serving architectures expose distinct prefill and decode behaviors, existing systems fail to exploit these phase differences for energy-efficient serving under strict latency SLOs. This paper introduces VoltanaLLM, the first system that explicitly targets and reduces the energy bloat in modern prefill-decode (P/D) disaggregated LLM serving. Guided by a control-theory perspective, VoltanaLLM separates two levers: per-instance operating-point selection (GPU frequency per iteration) and system-level state-space routing of requests. We empirically observe that LLM inference exhibits a U-shaped energy-frequency curve creating "sweet spots" that depend on phase behavior and load. VoltanaLLM exploits this by combining phase-specific, iteration-level frequency selection driven by a lightweight, online-adaptive latency predictor, with a decode state-space guided router that avoids architectural granularity-induced inefficiencies, all while meeting desired SLOs. We implement VoltanaLLM using SGLang and evaluate it across multiple models and real-world workloads. Our results show VoltanaLLM reduces end-to-end energy by up to 36.3% versus a static max-frequency baseline while maintaining high SLO attainment, and generalizes to newer GPUs. These results point to sustainable LLM serving via phase-aware, iteration-level frequency selection coupled with architecture-aware routing. Source code is available in https://github.com/Supercomputing-System-AI-Lab/VoltanaLLM.
Aug 9, 2025

PrismServe: Efficient LLM Serving on Heterogeneous Accelerator Clusters

Serving large language models across heterogeneous accelerators is challenging because partitioning a replica across device types introduces communication overhead during autoregressive decoding, while deploying complete quantized replicas can degrade model quality. We present PrismServe, a serving system that combines request-level collaboration across heterogeneous hardware with a mixture of quantized experts derived from the same foundation model. Each expert executes within a group of same-type accelerators in a single node, while a two-level router selects an expert based on predicted response quality and then selects a replica according to load and prefix-cache locality. Implemented on unmodified vLLM, PrismServe achieves 2.0--2.6×\times the throughput of cross-node or cross-vendor full-precision pipelined deployments and reduces P99 time per output token by 55--65% when serving Qwen3-14B on 48 accelerators from three vendors. Across Qwen3-8B, Qwen3-14B, and Qwen3-32B on five downstream tasks, PrismServe outperforms the best single quantization method by 2.0--4.3 points while remaining within 1.4 points of full-precision accuracy. Our code is available at https://anonymous.4open.science/r/LLM-Inference-System-B000/
Aug 8, 2025

LLM Serving Optimization with Variable Prefill and Decode Lengths

We study offline scheduling for large language model (LLM) serving under a fixed KV-cache memory budget, where requests have heterogeneous prompt (prefill) and response (decode) lengths. Given a backlog of requests available at time zero, the scheduler forms mixed prefill/decode batches over time to minimize total end-to-end latency. We show that heterogeneity in prompt lengths fundamentally changes the problem: minimizing total latency is NP-hard, and standard policies that prioritize short outputs or small total sequence sizes can have unbounded approximation ratios. We propose Sorted-F, which repeatedly selects feasible batches using an F-metric that balances batch cardinality against downstream decode cost. With exact batch selection, Sorted-F achieves a constant-factor approximation guarantee in the unit-time, uninterrupted-decoding model with known output lengths; the guarantee also holds under a static peak-memory batch constraint. We develop an exact pseudopolynomial dynamic program for this static subproblem, scalable local-search and greedy heuristics, LP-guided variants, and a receding-horizon online extension. Experiments on public conversational and long-document summarization workloads show that F-metric-based scheduling substantially reduces latency relative to standard baselines and remains close to the LP relaxation lower bound on tractable instances.
Jun 24, 2024

Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

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.