# MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs

arXiv: https://arxiv.org/abs/2411.11217 · HTML: https://mlsanity.com/paper/2411.11217/

## Key facts

- Cited by 73 papers in the map (data through 14 Oct 2026).
- Placed in Efficient MoE training and inference systems, one of 12 directions in Mixture-of-experts.
- Builds on 37 of its 57 references that are in the map.
- First posted on arXiv 18 Nov 2024.

## Placed in

- Mixture-of-experts / [Efficient MoE training and inference systems](https://mlsanity.com/moe/efficient-moe-training-and-inference-systems/)

## Builds on (most cited first, 30 of 37)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [GLaM: Efficient Scaling of Language Models with Mixture-of-Experts](https://mlsanity.com/paper/2112.06905/) (2021)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM](https://mlsanity.com/paper/2104.04473/) (2021)
- [Mixture-of-Experts with Expert Choice Routing](https://mlsanity.com/paper/2202.09368/) (2022)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [Efficiently Scaling Transformer Inference](https://mlsanity.com/paper/2211.05102/) (2022)
- [Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2406.10774/) (2024)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [Blockwise Parallel Decoding for Deep Autoregressive Models](https://mlsanity.com/paper/1811.03115/) (2018)
- [PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU](https://mlsanity.com/paper/2312.12456/) (2023)
- [Can Foundation Models Wrangle Your Data?](https://mlsanity.com/paper/2205.09911/) (2022)
- [Accelerating Transformer Inference for Translation via Parallel Decoding](https://mlsanity.com/paper/2305.10427/) (2023)

## Built on by (most cited first, 30 of 73)

- [A Survey on Inference Optimization Techniques for Mixture of Experts Models](https://mlsanity.com/paper/2412.14219/) (2024)
- [MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism](https://mlsanity.com/paper/2504.02263/) (2025)
- [Jenga: Effective Memory Management for Serving LLM with Heterogeneity](https://mlsanity.com/paper/2503.18292/) (2025)
- [D2MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving](https://mlsanity.com/paper/2504.15299/) (2025)
- [SLOs-Serve: Optimized Serving of Multi-SLO LLMs](https://mlsanity.com/paper/2504.08784/) (2025)
- [L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models](https://mlsanity.com/paper/2505.17505/) (2025)
- [Utility-Driven Speculative Decoding for Mixture-of-Experts](https://mlsanity.com/paper/2506.20675/) (2025)
- [Energy Use of AI Inference, Efficiency Pathways, and Test-Time Scaling](https://mlsanity.com/paper/2509.20241/) (2025)
- [eMoE: Task-aware Memory Efficient Mixture-of-Experts-Based (MoE) Model Inference](https://mlsanity.com/paper/2503.06823/) (2025)
- [MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems](https://mlsanity.com/paper/2505.11415/) (2025)
- [FloE: On-the-Fly MoE Inference on Memory-constrained GPU](https://mlsanity.com/paper/2505.05950/) (2025)
- [LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure](https://mlsanity.com/paper/2602.23036/) (2026)
- [Accelerating Mixture-of-Experts Inference by Hiding Offloading Latency with Speculative Decoding](https://mlsanity.com/paper/2508.21706/) (2025)
- [LayerScope: Predictive Cross-Layer Scheduling for Efficient Multi-Batch MoE Inference on Legacy Servers](https://mlsanity.com/paper/2509.23638/) (2025)
- [Janus: Disaggregating Attention and Experts for Scalable MoE Inference](https://mlsanity.com/paper/2512.13525/) (2025)
- [Patterns behind Chaos: Forecasting Data Movement for Efficient Large-Scale MoE LLM Inference](https://mlsanity.com/paper/2510.05497/) (2025)
- [CHIME: A Case for Efficient Long-Context Attention-FC Disaggregated Inference with DIMM-PIM](https://mlsanity.com/paper/2504.17584/) (2025)
- [ExpertFlow: Adaptive Expert Scheduling and Memory Coordination for Efficient MoE Inference](https://mlsanity.com/paper/2510.26730/) (2025)
- [FlexiCache: Leveraging Temporal Stability of Attention Heads for Efficient KV Cache Management](https://mlsanity.com/paper/2511.00868/) (2025)
- [MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios](https://mlsanity.com/paper/2603.09983/) (2026)
- [KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference](https://mlsanity.com/paper/2605.18071/) (2026)
- [A Cost-Effective Near-Storage Processing Solution for Offline Inference of Long-Context LLMs](https://mlsanity.com/paper/2502.09921/) (2025)
- [BrownoutServe: SLO-Aware Inference Serving under Bursty Workloads for MoE-based LLMs](https://mlsanity.com/paper/2507.17133/) (2025)
- [ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling](https://mlsanity.com/paper/2601.21198/) (2026)
- [Dynamic Expert Sharing: Decoupling Memory from Parallelism in Mixture-of-Experts Diffusion LLMs](https://mlsanity.com/paper/2602.00879/) (2026)
- [PCR: A Prefetch-Enhanced Cache Reuse System for Low-Latency RAG Serving](https://mlsanity.com/paper/2603.23049/) (2026)
- [Echo: Efficient Co-Scheduling of Hybrid Online-Offline Tasks for Large Language Model Serving](https://mlsanity.com/paper/2504.03651/) (2025)
- [MoE-Lens: Towards the Hardware Limit of High-Throughput MoE LLM Serving Under Resource Constraints](https://mlsanity.com/paper/2504.09345/) (2025)
- [SMoE: An Algorithm-System Co-Design for Pushing MoE to the Edge via Expert Substitution](https://mlsanity.com/paper/2508.18983/) (2025)
- [ShadowServe: Interference-Free KV Cache Fetching for Distributed Prefix Caching](https://mlsanity.com/paper/2509.16857/) (2025)

## Abstract (arXiv)

Efficient deployment of large language models, particularly Mixture of Experts (MoE), on resource-constrained platforms presents significant challenges, especially in terms of computational efficiency and memory utilization. The MoE architecture, renowned for its ability to increase model capacity without a proportional increase in inference cost, greatly reduces the token generation latency compared with dense models. However, the large model size makes MoE models inaccessible to individuals without high-end GPUs. In this paper, we propose a high-throughput MoE batch inference system, that significantly outperforms past work. MoE-Lightning introduces a novel CPU-GPU-I/O pipelining schedule, CGOPipe, with paged weights to achieve high resource utilization, and a performance model, HRM, based on a Hierarchical Roofline Model we introduce to help find policies with higher throughput than existing systems. MoE-Lightning can achieve up to 10.3x higher throughput than state-of-the-art offloading-enabled LLM inference systems for Mixtral 8x7B on a single T4 GPU (16GB). When the theoretical system throughput is bounded by the GPU memory, MoE-Lightning can reach the throughput upper bound with 2-3x less CPU memory, significantly increasing resource utilization. MoE-Lightning also supports efficient batch inference for much larger MoEs (e.g., Mixtral 8x22B and DBRX) on multiple low-cost GPUs (e.g., 2-4 T4).