Adaptive Request Scheduling for CodeLLM Serving with SLA Guarantees

• URL: http://arxiv.org/abs/2506.19677v2
• Date: Wed, 25 Jun 2025 16:13:14 GMT
• Title: Adaptive Request Scheduling for CodeLLM Serving with SLA Guarantees
• Abstract summary: Existing Large Language Models (CodeMs) are increasingly integrated into modern software development.<n>Yet, self-hosted environments remain a significant challenge in resource-constrained serving environments.<n>We propose SABER, a dynamic strategy that predicts per-request SLA feasibility and decisions in real time.<n>Our results demonstrate that SLA-aware, adaptive scheduling is key to robust, high-performance CodeLL serving.
• Score: 6.110847503516972
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Code Large Language Models (CodeLLMs) are increasingly integrated into modern software development workflows, yet efficiently serving them in resource-constrained, self-hosted environments remains a significant challenge. Existing LLM serving systems employs Continuous Batching for throughput improvement. However, they rely on static batch size configurations that cannot adapt to fluctuating request rates or heterogeneous workloads, leading to frequent SLA (Service Level Agreement) violations and unstable performance. In this study, We propose SABER, a dynamic batching strategy that predicts per-request SLA feasibility and adjusts decisions in real time. SABER improves goodput by up to 26% over the best static configurations and reduces latency variability by up to 45%, all without manual tuning or service restarts. Our results demonstrate that SLA-aware, adaptive scheduling is key to robust, high-performance CodeLLM serving.

Related papers

• DiLaServe: High SLO Attainment Serving for Diffusion Language Models [1.840765166456233]
  Diffusion language models (DLMs) offer higher inference throughput while maintaining competitive quality.<n>We present DiLaServe, a cluster-level serving system for DLMs.<n>Across multiple benchmarks and real-world traces, DiLaServe improves SLO attainment by up to 56.6 percentage points and reduces end-to-end request latency by up to 46%.
  arXiv  Detail & Related papers  (2026-06-27T21:21:53Z)
• SOPE: Stabilizing Off-Policy Evaluation for Online RL with Prior Data [49.370849653460716]
  We propose SOPE, an algorithm that uses an actor-aligned Off-Policy Policy Evaluation signal as an automated early-stopping mechanism.<n> evaluated on 25 continuous control tasks from the Minari benchmark suite.<n>SOPE improves baseline performance by up to 45.6% while reducing the required TFLOPs by up to 22x.
  arXiv  Detail & Related papers  (2026-05-07T08:32:09Z)
• AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering [52.67783579040657]
  AceGRPO is a machine learning system that prioritizes tasks at the agent's learning frontier to maximize learning efficiency.<n>Our trained Ace-30B model achieves a 100% valid submission rate on MLE-Bench-Lite, approaches the performance of proprietary frontier models, and outperforms larger open-source baselines.
  arXiv  Detail & Related papers  (2026-02-08T10:55:03Z)
• CALM: A Self-Adaptive Orchestration Approach for QoS-Aware Routing in Small Language Model based Systems [0.6999740786886536]
  CALM is a self-adaptive orchestration mechanism based on MAPE-K.<n>It reduces latency by approximately 40% and energy consumption by 50%.<n>Our evaluation shows that CALM reduces latency by approximately 40% and energy consumption by 50%.
  arXiv  Detail & Related papers  (2026-02-03T15:20:14Z)
• TS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy Acceleration [64.32072516882947]
  Diffusion Policy excels in embodied control but suffers from high inference latency and computational cost.<n>We propose Temporal-aware Reinforcement-based Speculative Diffusion Policy (TS-DP)<n>TS-DP achieves up to 4.17 times faster inference with over 94% accepted drafts, reaching an inference frequency of 25 Hz.
  arXiv  Detail & Related papers  (2025-12-13T07:53:14Z)
• AugServe: Adaptive Request Scheduling for Augmented Large Language Model Inference Serving [6.505016440664893]
  AugServe is an efficient inference framework designed to reduce queueing latency and enhance effective throughput for augmented large language models (LLMs)<n> Experimental results show that AugServe achieves 4.7-33.1x and 3.3-13.2x higher effective throughput than vLLM and InferCept, while reducing fluctuating time-to-first-token (TTFT) by up to 96.3% and 95.0%, respectively.
  arXiv  Detail & Related papers  (2025-12-03T17:49:38Z)
• Soft Adaptive Policy Optimization [67.61886077470528]
  Reinforcement learning plays an increasingly important role in enhancing the reasoning capabilities of large language models.<n>Existing group-based policy optimization methods, such as GSPO and GRPO, alleviate this problem via hard clipping.<n>We propose Soft Adaptive Policy Optimization (SAPO), which replaces hard clipping with a smooth, temperature-controlled gate.
  arXiv  Detail & Related papers  (2025-11-25T14:25:19Z)
• Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning [77.92320830700797]
  Reinforcement Learning has played a central role in enabling reasoning capabilities of Large Language Models.<n>We propose a tractable computational framework that tracks and leverages curvature information during policy updates.<n>The algorithm, Curvature-Aware Policy Optimization (CAPO), identifies samples that contribute to unstable updates and masks them out.
  arXiv  Detail & Related papers  (2025-10-01T12:29:32Z)
• Dynamic Speculative Agent Planning [57.630218933994534]
  Large language-model-based agents face critical deployment challenges due to prohibitive latency and inference costs.<n>We introduce Dynamic Speculative Planning (DSP), an online reinforcement learning framework that provides lossless acceleration with substantially reduced costs.<n>Experiments on two standard agent benchmarks demonstrate that DSP achieves comparable efficiency to the fastest acceleration method while reducing total cost by 30% and unnecessary cost up to 60%.
  arXiv  Detail & Related papers  (2025-09-02T03:34:36Z)
• SLA-MORL: SLA-Aware Multi-Objective Reinforcement Learning for HPC Resource Optimization [0.9026828778470117]
  We present SLA-MORL, an adaptive multi-objective reinforcement learning framework that intelligently allocates resources based on user-defined preferences.<n>We show that SLA-MORL achieves 67.2% reduction in training time for deadline-critical jobs, 68.8% reduction in costs for budget-constrained workloads, and 73.4% improvement in overall SLA compliance compared to static baselines.
  arXiv  Detail & Related papers  (2025-08-05T14:37:24Z)
• Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs [48.653022530291494]
  Large language models (LLMs) have shown remarkable performance across diverse reasoning and generation tasks.<n>This work presents the first systematic study of this latency quality trade off in real time decision making tasks.<n>We propose FPX, an adaptive framework that dynamically selects model size and quantization level based on real time demands.
  arXiv  Detail & Related papers  (2025-05-26T04:03:48Z)
• Efficient and Workload-Aware LLM Serving via Runtime Layer Swapping and KV Cache Resizing [15.386746669464964]
  MorphServe is a workload-aware LLM serving framework based on morphological adaptation.<n>It reduces average SLO violations by 92.45 percent and improves the P95 TTFT latency by 2.2x-3.9x compared to full-precision serving.
  arXiv  Detail & Related papers  (2025-05-24T06:12:31Z)
• DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal [55.13854171147104]
  Large Language Models (LLMs) have revolutionized various domains, including natural language processing, data analysis, and software development.<n>We present Dynamic Action Re-Sampling (DARS), a novel inference time compute scaling approach for coding agents.<n>We evaluate our approach on SWE-Bench Lite benchmark, demonstrating that this scaling strategy achieves a pass@k score of 55% with Claude 3.5 Sonnet V2.
  arXiv  Detail & Related papers  (2025-03-18T14:02:59Z)
• SpecServe: Efficient and SLO-Aware Large Language Model Serving with Adaptive Speculative Decoding [18.45994543035372]
  Speculative decoding has emerged as a compelling technique to accelerate Large Language Model inference.<n>Existing speculative decoding solutions often fail to adapt to varying workloads and system environments.<n>We introduce SpecServe, an efficient LLM inference system that dynamically adjusts speculative strategies according to real-time request loads.
  arXiv  Detail & Related papers  (2025-03-07T02:27:51Z)
• LADs: Leveraging LLMs for AI-Driven DevOps [3.240228178267042]
  LADs is a principled approach to configuration optimization through in-depth analysis of what optimization works under which conditions.<n>By leveraging Retrieval-Augmented Generation, Few-Shot Learning, Chain-of-Thought, and Feedback-Based Prompt Chaining, LADs generates accurate configurations and learns from deployment failures to iteratively refine system settings.<n>Our findings reveal key insights into the trade-offs between performance, cost, and scalability, helping practitioners determine the right strategies for different deployment scenarios.
  arXiv  Detail & Related papers  (2025-02-28T08:12:08Z)
• Dynamic Noise Preference Optimization for LLM Self-Improvement via Synthetic Data [51.62162460809116]
  We introduce Dynamic Noise Preference Optimization (DNPO) to ensure consistent improvements across iterations.<n>In experiments with Zephyr-7B, DNPO consistently outperforms existing methods, showing an average performance boost of 2.6%.<n> DNPO shows a significant improvement in model-generated data quality, with a 29.4% win-loss rate gap compared to the baseline in GPT-4 evaluations.
  arXiv  Detail & Related papers  (2025-02-08T01:20:09Z)
• Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization [61.02719787737867]
  Large language models (LLMs) are increasingly deployed and democratized on edge devices.<n>One promising solution is uncertainty-based SLM routing, offloading high-stakes queries to stronger LLMs when resulting in low-confidence responses on SLM.<n>We conduct a comprehensive investigation into benchmarking and generalization of uncertainty-driven routing strategies from SLMs to LLMs over 1500+ settings.
  arXiv  Detail & Related papers  (2025-02-06T18:59:11Z)
• 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)
• SPEQ: Offline Stabilization Phases for Efficient Q-Learning in High Update-To-Data Ratio Reinforcement Learning [51.10866035483686]
  High update-to-data (UTD) ratio algorithms in reinforcement learning (RL) improve sample efficiency but incur high computational costs, limiting real-world scalability.<n>We propose Offline Stabilization Phases for Efficient Q-Learning (SPEQ), an RL algorithm that combines low-UTD online training with periodic offline stabilization phases.<n>During these phases, Q-functions are fine-tuned with high UTD ratios on a fixed replay buffer, reducing redundant updates on suboptimal data.
  arXiv  Detail & Related papers  (2025-01-15T09:04:19Z)
• Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization [71.87335804334616]
  Federated learning (FL) is a promising paradigm to enable collaborative model training with decentralized data. The training process of Large Language Models (LLMs) generally incurs the update of significant parameters. This paper proposes an efficient partial prompt tuning approach to improve performance and efficiency simultaneously.
  arXiv  Detail & Related papers  (2023-10-23T16:37:59Z)
• Reconciling High Accuracy, Cost-Efficiency, and Low Latency of Inference Serving Systems [0.0]
  InfAdapter proactively selects a set of ML model variants with their resource allocations to meet latency SLO. It decreases SLO violation and costs up to 65% and 33%, respectively, compared to a popular industry autoscaler.
  arXiv  Detail & Related papers  (2023-04-21T11:19:49Z)

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.