# HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference

arXiv: https://arxiv.org/abs/2504.05897 · HTML: https://mlsanity.com/paper/2504.05897/

## Key facts

- Cited by 16 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 19 of its 30 references that are in the map.
- First posted on arXiv 8 Apr 2025.

## 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, 19 of 19)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU](https://mlsanity.com/paper/2312.12456/) (2023)
- [Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference](https://mlsanity.com/paper/2308.12066/) (2023)
- [Fast Inference of Mixture-of-Experts Language Models with Offloading](https://mlsanity.com/paper/2312.17238/) (2023)
- [Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models](https://mlsanity.com/paper/2402.07033/) (2024)
- [HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference](https://mlsanity.com/paper/2411.01433/) (2024)
- [AdapMoE: Adaptive Sensitivity-based Expert Gating and Management for Efficient MoE Inference](https://mlsanity.com/paper/2408.10284/) (2024)
- [ProMoE: Fast MoE-based LLM Serving using Proactive Caching](https://mlsanity.com/paper/2410.22134/) (2024)
- [CaraServe: CPU-Assisted and Rank-Aware LoRA Serving for Generative LLM Inference](https://mlsanity.com/paper/2401.11240/) (2024)
- [Adaptive Gating in Mixture-of-Experts based Language Models](https://mlsanity.com/paper/2310.07188/) (2023)

## Built on by (most cited first, 16 of 16)

- [MoE-SpeQ: Speculative Quantized Decoding with Proactive Expert Prefetching and Offloading for Mixture-of-Experts](https://mlsanity.com/paper/2511.14102/) (2025)
- [TEAM: Temporal-Spatial Consistency Guided Expert Activation for MoE Diffusion Language Model Acceleration](https://mlsanity.com/paper/2602.08404/) (2026)
- [MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios](https://mlsanity.com/paper/2603.09983/) (2026)
- [HGCA: Hybrid GPU-CPU Attention for Long Context LLM Inference](https://mlsanity.com/paper/2507.03153/) (2025)
- [SMoE: An Algorithm-System Co-Design for Pushing MoE to the Edge via Expert Substitution](https://mlsanity.com/paper/2508.18983/) (2025)
- [FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution](https://mlsanity.com/paper/2608.16157/) (2026)
- [Ban&Pick: Enhancing Performance and Efficiency of MoE-LLMs via Smarter Routing](https://mlsanity.com/paper/2509.06346/) (2025)
- [Remoe: Towards Efficient and Low-Cost MoE Inference in Serverless Computing](https://mlsanity.com/paper/2512.18674/) (2025)
- [DALI: A Workload-Aware Offloading Framework for Efficient MoE Inference on Local PCs](https://mlsanity.com/paper/2602.03495/) (2026)
- [WiSP: A Working-Set View of Mixture-of-Experts Serving on Extremely Low-Resource Hardware](https://mlsanity.com/paper/2606.21868/) (2026)
- [Noesis: Bidirectional Graph-RAG with Adaptive Parallelism and Cross-Knowledge-Base Semantic Discovery](https://mlsanity.com/paper/2608.15919/) (2026)
- [VisMMOE: Exploiting Visual-Expert Affinity for Efficient Visual-Language MoE Offloading](https://mlsanity.com/paper/2605.05899/) (2026)
- [Automated Tensor Scheduling for Hybrid CPU-GPU LLM Inference on Consumer Devices](https://mlsanity.com/paper/2607.10183/) (2026)
- [HDA-MoE: Hybrid Parallelism and Dynamic, Adaptive Scheduling for Mixture-of-Experts with 3D Near-Memory Processing](https://mlsanity.com/paper/2609.08682/) (2026)
- [Physically Partitioned KVCache Format for CPU--GPU Load Balancing in MoE Inference](https://mlsanity.com/paper/2609.14507/) (2026)
- [BigMoMo: Efficient Inference of Large-Scale MoE with Speculative Decoding on Mobile Devices](https://mlsanity.com/paper/2609.14643/) (2026)

## Abstract (arXiv)

The Mixture of Experts (MoE) architecture has demonstrated significant advantages as it enables to increase the model capacity without a proportional increase in computation. However, the large MoE model size still introduces substantial memory demands, which usually requires expert offloading on resource-constrained platforms and incurs significant overhead. Hybrid CPU-GPU inference has been proposed to leverage CPU computation to reduce expert loading overhead but faces major challenges: on one hand, the expert activation patterns of MoE models are highly unstable, rendering the fixed mapping strategies in existing works inefficient; on the other hand, the hybrid CPU-GPU schedule for MoE is inherently complex due to the diverse expert sizes, structures, uneven workload distribution, etc. To address these challenges, in this paper, we propose HybriMoE, a hybrid CPU-GPU inference framework that improves resource utilization through a novel CPU-GPU scheduling and cache management system. HybriMoE introduces (i) a dynamic intra-layer scheduling strategy to balance workloads across CPU and GPU, (ii) an impact-driven inter-layer prefetching algorithm, and (iii) a score-based caching algorithm to mitigate expert activation instability. We implement HybriMoE on top of the kTransformers framework and evaluate it on three widely used MoE-based LLMs. Experimental results demonstrate that HybriMoE achieves an average speedup of 1.33× in the prefill stage and 1.70× in the decode stage compared to state-of-the-art hybrid MoE inference framework. Our code is available at: https://github.com/PKU-SEC-Lab/HybriMoE.