# Efficient MoE training and inference systems Area: [Mixture-of-experts](https://mlsanity.com/moe/index.md). HTML: https://mlsanity.com/moe/efficient-moe-training-and-inference-systems/ ## Key facts - Efficient MoE training and inference systems: 386 papers on arXiv since 2020 (data through 14 Oct 2026). - 107 of its 386 mapped papers (28%) cite “DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale” (2022, arXiv 2201.05596). - 86 of its 386 mapped papers (22%) cite “Tutel: Adaptive Mixture-of-Experts at Scale” (2022, arXiv 2206.03382). - 30 new papers 17 Sep–14 Oct. ## Most cited here - [DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale](https://mlsanity.com/paper/2201.05596/) (2022), cited by 107 papers here - [Tutel: Adaptive Mixture-of-Experts at Scale](https://mlsanity.com/paper/2206.03382/) (2022), cited by 86 papers here - [Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference](https://mlsanity.com/paper/2308.12066/) (2023), cited by 77 papers here - [Accelerating Distributed MoE Training and Inference with Lina](https://mlsanity.com/paper/2210.17223/) (2022), cited by 67 papers here - [Fast Inference of Mixture-of-Experts Language Models with Offloading](https://mlsanity.com/paper/2312.17238/) (2023), cited by 59 papers here - [MegaBlocks: Efficient Sparse Training with Mixture-of-Experts](https://mlsanity.com/paper/2211.15841/) (2022), cited by 53 papers here - [Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models](https://mlsanity.com/paper/2402.07033/) (2024), cited by 48 papers here - [MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs](https://mlsanity.com/paper/2411.11217/) (2024), cited by 45 papers here - [AdapMoE: Adaptive Sensitivity-based Expert Gating and Management for Efficient MoE Inference](https://mlsanity.com/paper/2408.10284/) (2024), cited by 36 papers here - [HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference](https://mlsanity.com/paper/2411.01433/) (2024), cited by 36 papers here ## New (17 Sep–14 Oct) - [FastEEP: Fast Intra-Instance Elastic Scaling for Expert-Parallel MoE Serving](https://mlsanity.com/paper/2610.18451/) (2026-10-13) - [FORGE: Procedural Weight Generation for Sparse MoE Inference](https://mlsanity.com/paper/2610.16890/) (2026-10-12) - [SpecFit: Not All Draft Tokens Cost the Same in Offloaded MoE Inference](https://mlsanity.com/paper/2610.15417/) (2026-10-11) - [One Model, Multiple Compute Budgets: Multi-Ratio ConceptMoE for Flexible Compute Across Turns](https://mlsanity.com/paper/2610.14074/) (2026-10-08) - [STAPLE: Static Sparse Upcycling of Pretrained Checkpoints via Embedding Modules](https://mlsanity.com/paper/2610.12599/) (2026-10-08) - [Democratizing MoE inference on commodity GPUs with CoMoE](https://mlsanity.com/paper/2610.09424/) (2026-10-07) - [Expert Coupling in MoE Pretraining: Reducing All-to-All Overhead with Correlated Placement and Token Shuffling](https://mlsanity.com/paper/2610.09372/) (2026-10-07) - [Stepped MoE: Segment-Level Routing with Configurable Inference Complexity](https://mlsanity.com/paper/2610.07348/) (2026-10-05) - [Cascadia: Resident 975B MoE Inference on Eleven AI PCs](https://mlsanity.com/paper/2610.07219/) (2026-10-05) - [CIPHER-MoE: Balancing Efficiency and Routing Fidelity in Trillion-Scale MoE Training](https://mlsanity.com/paper/2610.05744/) (2026-10-05) - [Universal Test-Time Training](https://mlsanity.com/paper/2610.05484/) (2026-10-04) - [Efficient Expert-Parallel Communication on PCIe-Connected Consumer GPUs](https://mlsanity.com/paper/2609.40093/) (2026-09-30) - [HAPMoE: Heterogeneity-Aware Automatic Parallelism Planning for Mixture-of-Experts Models Training](https://mlsanity.com/paper/2609.39350/) (2026-09-30) - [Hardware-Native Joint Sparse-Quantization for Trillion-Scale Mixture-of-Experts](https://mlsanity.com/paper/2610.02241/) (2026-09-29) - [Mira: Memory-Efficient MoE Inference Using Adaptive Caching and Predictive Expert Staging](https://mlsanity.com/paper/2609.38090/) (2026-09-29) - [BASE: Batch-Aware Selection of Experts Using Predicted Removal Error for Efficient MoE Decoding](https://mlsanity.com/paper/2609.36222/) (2026-09-28) - [Mixture-of-Kittens: MoE Megakernel for NVL72s](https://mlsanity.com/paper/2609.36070/) (2026-09-28) - [TopoEP: Topology-Aware Load Balancing for Expert-Parallel MoE Training](https://mlsanity.com/paper/2609.35481/) (2026-09-28) - [SlimWise: Decoupling Expert Pruning Across Prefill and Decode for Efficient MoE Serving](https://mlsanity.com/paper/2609.34117/) (2026-09-28) - [MaskCoFT: Masked Co-Adaptive Fine-Tuning for Memory-Efficient MoE Inference](https://mlsanity.com/paper/2609.34077/) (2026-09-28) - [CipherGenome: Homomorphic Inference for Genomic Mixture-of-Experts](https://mlsanity.com/paper/2609.35883/) (2026-09-27) - [GenomeOcean Anywhere: Private WebGPU Inference for Genome MoEs](https://mlsanity.com/paper/2609.35882/) (2026-09-27) - [OLED-MoE: Accelerating MoE-Based dLLM Inference via Inter-Iteration Locality-Aware Expert Offloading](https://mlsanity.com/paper/2609.33385/) (2026-09-27) - [Paging the Experts: A Reproducible Characterization of Flash-Backed MoE Inference on iPhone](https://mlsanity.com/paper/2609.29032/) (2026-09-24) - [Exact Quantile Balancing and Load-Error Injection for Mixture-of-Experts](https://mlsanity.com/paper/2609.28053/) (2026-09-23) - [Logit-Aware MIMO AirComp for Distributed Mixture-of-Experts LLM Inference over Wireless Edge Networks](https://mlsanity.com/paper/2610.03741/) (2026-09-22) - [Efficient Mixture-of-Experts with Speculative Decoding via Expert Coactivation](https://mlsanity.com/paper/2609.22471/) (2026-09-18) - [Weave: Fine-Grained Dynamic SM Scheduling in an MoE Megakernel for Compute-Communication Overlap](https://mlsanity.com/paper/2609.21483/) (2026-09-18) - [A Multi-Engine Dataflow for MoE Decoding on Scratchpad-Based Tensor Accelerators](https://mlsanity.com/paper/2609.21137/) (2026-09-17) - [DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression](https://mlsanity.com/paper/2609.19969/) (2026-09-17)