MACE: A Hybrid LLM Serving System with Colocated SLO-aware Continuous Retraining Alignment

• URL: http://arxiv.org/abs/2510.03283v1
• Date: Sun, 28 Sep 2025 18:45:28 GMT
• Title: MACE: A Hybrid LLM Serving System with Colocated SLO-aware Continuous Retraining Alignment
• Authors: Yufei Li, Yu Fu, Yue Dong, Cong Liu,
• Abstract summary: Large language models (LLMs) deployed on edge servers are increasingly used in latency-sensitive applications such as personalized assistants, recommendation, and content moderation.<n>Existing retraining strategies either delay model updates, over-commit resources to retraining, or overlook iteration-level retraining granularity.<n>We propose MACE, a hybrid LLM system that colocates concurrent inference (prefill, decode) and fine-tuning, with intelligent memory management to maximize task performance while promising inference throughput.
• Score: 14.392166280035122
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large language models (LLMs) deployed on edge servers are increasingly used in latency-sensitive applications such as personalized assistants, recommendation, and content moderation. However, the non-stationary nature of user data necessitates frequent retraining, which introduces a fundamental tension between inference latency and model accuracy under constrained GPU resources. Existing retraining strategies either delay model updates, over-commit resources to retraining, or overlook iteration-level retraining granularity. In this paper, we identify that iteration-level scheduling is crucial for adapting retraining frequency to model drift without violating service-level objectives (SLOs). We propose MACE, a hybrid LLM system that colocates concurrent inference (prefill, decode) and fine-tuning, with intelligent memory management to maximize task performance while promising inference throughput. MACE leverages the insight that not all model updates equally affect output alignment and allocates GPU cycles accordingly to balance throughput, latency, and update freshness. Our trace-driven evaluation shows that MACE matches or exceeds continuous retraining while reducing inference latency by up to 63% and maintaining throughput under resource constraints. Compared to periodic retraining, MACE improves latency breakdown across prefill, decode, and finetune stages, and sustains GPU utilization above 85% in NVIDIA AGX Orin. These results demonstrate that iteration-level hybrid scheduling is a promising direction for deploying LLMs with continual learning capabilities on edge platforms.

Related papers

• 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)
• Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates [53.3717573880076]
  We introduce Just-In-Time Reinforcement Learning (JitRL), a training-free framework that enables test-time policy optimization without any gradient updates.<n>JitRL maintains a dynamic, non-parametric memory of experiences and retrieves relevant trajectories to estimate action advantages on-the-fly.<n>Experiments on WebArena and Jericho demonstrate that JitRL establishes a new state-of-the-art among training-free methods.
  arXiv  Detail & Related papers  (2026-01-26T14:16:51Z)
• Hybrid Learning and Optimization-Based Dynamic Scheduling for DL Workloads on Heterogeneous GPU Clusters [0.8445876768837571]
  We present RLTune, an application-agnostic reinforcement learning (RL)-based scheduling framework that dynamically prioritizes and allocates deep learning jobs on heterogeneous GPU clusters.<n>RLTune improves GPU utilization by up to 20%, reduces queueing delay by up to 81%, and shortens JCT by as much as 70 percent.<n>Unlike prior approaches, RLTune generalizes across diverse workloads without requiring per-job profiling.
  arXiv  Detail & Related papers  (2025-12-11T04:19:44Z)
• AReaL-Hex: Accommodating Asynchronous RL Training over Heterogeneous GPUs [24.96730768606278]
  We present AReaL-Hex, a heterogeneous-aware asynchronous RL training system.<n>It effectively schedules how to execute rollout generation and policy model training over heterogeneous GPUs.<n>It delivers up to 1.50x higher training throughput and 1.46x reduction in training cost.
  arXiv  Detail & Related papers  (2025-11-02T04:17:30Z)
• Semantic-Aware Scheduling for GPU Clusters with Large Language Models [60.14838697778884]
  We propose SchedMate, a framework that bridges the semantic gap between schedulers and jobs they manage.<n>SchedMate extracts deep insights from overlooked, unstructured data sources: source code, runtime logs, and historical jobs.<n>We show SchedMate reduces average job completion times by up to 1.91x, substantially enhancing the scheduling performance.
  arXiv  Detail & Related papers  (2025-10-02T02:01:02Z)
• AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning [23.24949857136035]
  Reinforcement learning (RL) has become a dominant paradigm for training large language models (LLMs)<n>We present AReaL, a fully asynchronous RL system that completely decouples generation from training.
  arXiv  Detail & Related papers  (2025-05-30T07:18:25Z)
• SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training [60.9776082805359]
  Large Language Models (LLMs) have demonstrated exceptional performance across diverse tasks, yet their training remains highly resource-intensive and susceptible to training instability.<n>This paper presents a comprehensive investigation into gradient spikes observed during LLM training, revealing their prevalence across multiple architectures and datasets.<n>We propose Spike-Aware Adam with Momentum Reset, a novel designed to counteract gradient spikes through momentum reset and spike-aware clipping.
  arXiv  Detail & Related papers  (2025-01-12T15:21:22Z)
• LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging [80.17238673443127]
  LiNeS is a post-training editing technique designed to preserve pre-trained generalization while enhancing fine-tuned task performance.<n>LiNeS demonstrates significant improvements in both single-task and multi-task settings across various benchmarks in vision and natural language processing.
  arXiv  Detail & Related papers  (2024-10-22T16:26:05Z)
• SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning [63.93193829913252]
  We propose an innovative METL strategy called SHERL for resource-limited scenarios. In the early route, intermediate outputs are consolidated via an anti-redundancy operation. In the late route, utilizing minimal late pre-trained layers could alleviate the peak demand on memory overhead.
  arXiv  Detail & Related papers  (2024-07-10T10:22:35Z)
• One QuantLLM for ALL: Fine-tuning Quantized LLMs Once for Efficient Deployments [43.107261545706415]
  Large Language Models (LLMs) have advanced rapidly but face significant memory demands. Current methods typically require lengthy training to alleviate the performance degradation from quantization loss. We make an initial attempt to extend the once-for-all framework to large language models.
  arXiv  Detail & Related papers  (2024-05-30T16:05:15Z)
• 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.