MAPS: Memory-Aware Predictive Scheduling Framework for Large Language Model Serving

arXiv:2609.15359 · cs.AI · Submitted 2026-09-14 · Read on arXiv

cs.AI

Submitted: 2026-09-14

Updated: 2026-09-14

Comments: 18 pages, 14 figures. Accepted at ICML 2026

Code: https://github.com/microsoft/DeepSpeed-MII

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Calibration — 26× in this paper · explained in 7 episodes
• KV cache — 19× in this paper · explained in 3 episodes
• Decode — 14× in this paper · explained in 2 episodes
• Adaptation — 11× in this paper · explained in 1 episode
• Accuracy — 9× in this paper · explained in 1 episode
• Ablation — 6× in this paper · explained in 1 episode
• Robustness — 6× in this paper · explained in 5 episodes
• Trace — 5× in this paper · explained in 2 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Ablation study — 3× in this paper · explained in 1 episode
• Abstraction — 3× in this paper · explained in 1 episode
• Conformal Prediction — 2× in this paper · explained in 5 episodes
• Core — 2× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 2× in this paper · explained in 3 episodes
• LoRA Adaptation — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Cooperation — 1× in this paper · explained in 2 episodes
• Edge Devices — 1× in this paper · explained in 2 episodes
• Energy Efficiency — 1× in this paper · explained in 3 episodes
• Exchangeability — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• LoRA Fine-Tuning — 1× in this paper · explained in 3 episodes
• Maximum Capacity — 1× in this paper
• Minimum Queue — 1× in this paper
• Parameter-Efficient Fine-Tuning — 1× in this paper · explained in 2 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Runtime State Collection — 1× in this paper

Sources

• Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads
• Qwen2.5 Technical Report
• PerLLM: Personalized Inference Scheduling with Edge-Cloud Collaboration for Diverse LLM Services

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection