DAOP: Data-Aware Offloading and Predictive Pre-Calculation for Efficient MoE Inference

arXiv:2501.10375 · cs.DC, cs.LG · Submitted 2026-08-21 · Read on arXiv

Yujie Zhang, Shivam Aggarwal, Tulika Mitra

cs.DC, cs.LG

Submitted: 2026-08-21

Updated: 2026-08-24

Comments: 7 pages, 10 figures, Accepted by DATE Conference 2025

Code: https://github.com/ecolab-nus/DAOP

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

Terminology

• Accuracy — 27× in this paper · explained in 1 episode
• Decode — 14× in this paper · explained in 2 episodes
• Transformer — 6× in this paper · explained in 2 episodes
• Expert Cache Ratio — 4× in this paper
• Mixture-of-Experts (MoE) — 4× in this paper · explained in 7 episodes
• Quantization — 4× in this paper · explained in 12 episodes
• Energy Efficiency — 3× in this paper · explained in 3 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Graceful Degradation — 3× in this paper · explained in 2 episodes
• Sparsity — 3× in this paper · explained in 4 episodes
• Calibration — 2× in this paper · explained in 7 episodes
• Downstream Tasks — 2× in this paper · explained in 2 episodes
• Mixture-of-Experts (MoE) Models — 2× in this paper · explained in 3 episodes
• Pruning — 2× in this paper · explained in 4 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Attention Mechanism — 1× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• LLMs with Mixture-of-Experts — 1× in this paper
• Mixture of Experts — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Mixtral of Experts
• Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models
• LLaMA: Open and Efficient Foundation Language Models
• Fast Inference of Mixture-of-Experts Language Models with Offloading
• MoE-Infinity: Efficient MoE Inference on Personal Machines with Sparsity-Aware Expert Cache
• EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices
• Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models
• A Review of Sparse Expert Models in Deep Learning
• A Survey on Mixture of Experts in Large Language Models
• HellaSwag: Can a Machine Really Finish Your Sentence?
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Training Verifiers to Solve Math Word Problems
• Measuring Massive Multitask Language Understanding
• TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension

Related papers

• iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
• Load Balancing with Evolving Workloads in Large-Scale Language Model Serving
• Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation
• SAMM: Sharded Automated Market Maker
• InferScale: GPU-Native KV Injection for Personalized LLM Serving
• Vigil: Accountable Liveness against Selective Silence