PLA-Serve: A Prefill-Length-Aware LLM Serving System

• URL: http://arxiv.org/abs/2601.11589v1
• Date: Sun, 04 Jan 2026 18:14:24 GMT
• Title: PLA-Serve: A Prefill-Length-Aware LLM Serving System
• Authors: Jianshu She, Zonghang Li, Hongchao Du, Shangyu Wu, Wenhao Zheng, Eric Xing, Zhengzhong Liu, Huaxiu Yao, Jason Xue, Qirong Ho,
• Abstract summary: PLA-Serve identifies and disaggregates requests with different prompt lengths to reduce TTFT latency.<n>We observe that prompt-length variations lead to distinct bottlenecks, motivating an adaptive scheduling strategy.<n> PLA-Serve reduces prefill latency by over 30% compared to vanilla SG under prefill**-Lang**decode disaggregation.
• Score: 33.313531352453346
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: PLA-Serve 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. PLA-Serve 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, PLA-Serve 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, PLA-Serve improves request throughput by 35% serving Qwen2.5-32B model for prefill instance, demonstrating its effectiveness in optimizing heterogeneous LLM serving workloads.

Related papers

• HALO: Semantic-Aware Distributed LLM Inference in Lossy Edge Network [50.33808558714122]
  Large language models' (LLMs) inference at the edge can facilitate prompt service responsiveness while protecting user privacy.<n>We propose HALO, a novel framework that can boost the distributed LLM inference in lossy edge network.<n> Experimental results from a Raspberry Pi cluster demonstrate that HALO achieves a 3.41x end-to-end speedup for LLaMA-series LLMs under unreliable network conditions.
  arXiv  Detail & Related papers  (2026-01-16T07:37:23Z)
• Why Should the Server Do It All?: A Scalable, Versatile, and Model-Agnostic Framework for Server-Light DNN Inference over Massively Distributed Clients via Training-Free Intermediate Feature Compression [6.932768187544348]
  We introduce SLICER, a retraining-free, architecture-agnostic framework that compresses IFs to reduce both communication and server load in split computing.<n>Across standard vision and LLM workloads, SLICER reduces uplink volume by up to 10x and server GPU time by up to 4.4x.
  arXiv  Detail & Related papers  (2025-11-03T08:44:13Z)
• CSGO: Generalized Optimization for Cold Start in Wireless Collaborative Edge LLM Systems [62.24576366776727]
  We propose a latency-aware scheduling framework to minimize total inference latency.<n>We show that the proposed method significantly reduces cold-start latency compared to baseline strategies.
  arXiv  Detail & Related papers  (2025-08-15T07:49:22Z)
• BucketServe: Bucket-Based Dynamic Batching for Smart and Efficient LLM Inference Serving [3.620158146761518]
  BucketServe is a bucket-based dynamic framework designed to optimize inference performance.<n>It can handle 1.93x more request load load attainment of 80% compared with UELLM and demonstrates 1.975x higher system load capacity compared to the UELLM.
  arXiv  Detail & Related papers  (2025-07-23T01:51:48Z)
• PolyServe: Efficient Multi-SLO Serving at Scale [6.147741784378271]
  PolyServe is a novel multi-SLO scheduling policy at scale that maintains high SLO attainment while maximizing throughput.<n> PolyServe achieves 1.23x goodput gain compared to existing policies, achieving up to 92.5% of optimal goodput.
  arXiv  Detail & Related papers  (2025-07-17T05:54:42Z)
• AdaServe: Accelerating Multi-SLO LLM Serving with SLO-Customized Speculative Decoding [12.106234303559571]
  We present AdaServe, the first serving system designed to support efficient multi-SLO serving through SLO-customized speculative decoding.<n>AdaServe formulates multi-SLO serving as a constrained optimization problem and introduces a hardware-aware algorithm.<n>It features a speculate-select-verify pipeline that enables fine-grained control over decoding speed while maximizing system throughput.
  arXiv  Detail & Related papers  (2025-01-21T14:15:01Z)
• Progressive Mixed-Precision Decoding for Efficient LLM Inference [49.05448842542558]
  We introduce Progressive Mixed-Precision Decoding (PMPD) to address the memory-boundedness of decoding.<n>PMPD achieves 1.4$-$12.2$times$ speedup in matrix-vector multiplications over fp16 models.<n>Our approach delivers a throughput gain of 3.8$-$8.0$times$ over fp16 models and up to 1.54$times$ over uniform quantization approaches.
  arXiv  Detail & Related papers  (2024-10-17T11:46:33Z)
• ConServe: Fine-Grained GPU Harvesting for LLM Online and Offline Co-Serving [61.35068981176018]
  ConServe is a large language model (LLM) serving system that achieves high throughput and strong online latency guarantees.<n>We show that ConServe delivers an average of 2.2$times$ higher throughput and reduces online serving tail latency by 2.9$times$ on average compared to state-of-the-art systems.
  arXiv  Detail & Related papers  (2024-10-02T04:12:13Z)
• HiRE: High Recall Approximate Top-$k$ Estimation for Efficient LLM Inference [68.59839755875252]
  HiRE comprises of two novel components: (i) a compression scheme to cheaply predict top-$k$ rows/columns with high recall, followed by full computation restricted to the predicted subset, and (ii) DA-TOP-$k$: an efficient multi-device approximate top-$k$ operator. We demonstrate that on a one billion parameter model, HiRE applied to both the softmax as well as feedforward layers, achieves almost matching pretraining and downstream accuracy, and speeds up inference latency by $1.47times$ on a single TPUv5e device.
  arXiv  Detail & Related papers  (2024-02-14T18:04:36Z)
• SpotServe: Serving Generative Large Language Models on Preemptible Instances [64.18638174004151]
  SpotServe is the first distributed large language models serving system on preemptible instances. We show that SpotServe can reduce the P99 tail latency by 2.4 - 9.1x compared with the best existing LLM serving systems. We also show that SpotServe can leverage the price advantage of preemptive instances, saving 54% monetary cost compared with only using on-demand instances.
  arXiv  Detail & Related papers  (2023-11-27T06:31:17Z)
• Fast Distributed Inference Serving for Large Language Models [12.703624317418237]
  We present FastServe, a distributed inference serving system for large language models (LLMs) FastServe exploits the autoregressive pattern of LLM inference to enable preemption at the granularity of each output token. We build a system prototype of FastServe and experimental results show that compared to the state-of-the-art solution vLLM, FastServe improves the throughput by up to 31.4x and 17.9x under the same average and tail latency requirements, respectively.
  arXiv  Detail & Related papers  (2023-05-10T06:17:50Z)
• Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networks [44.37047471448793]
  In this paper, we advocate the integration of edge computing paradigm and parallel split learning (PSL) We propose an innovative PSL framework, namely, efficient parallel split learning (EPSL) to accelerate model training. We show that the proposed EPSL framework significantly decreases the training latency needed to achieve a target accuracy.
  arXiv  Detail & Related papers  (2023-03-26T16:09:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.