# SpaceMoE: Realizing Distributed Mixture-of-Experts Inference over Space Networks

arXiv: https://arxiv.org/abs/2605.00515 · HTML: https://mlsanity.com/paper/2605.00515/

## Key facts

- Cited by 3 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 41 references that are in the map.
- First posted on arXiv 1 May 2026.

## 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)

- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Efficient Processing of Deep Neural Networks: A Tutorial and Survey](https://mlsanity.com/paper/1703.09039/) (2017)
- [Beyond Data and Model Parallelism for Deep Neural Networks](https://mlsanity.com/paper/1807.05358/) (2018)
- [LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training](https://mlsanity.com/paper/2406.16554/) (2024)
- [Towards an Intelligent Edge: Wireless Communication Meets Machine Learning](https://mlsanity.com/paper/1809.00343/) (2018)
- [Communication-Computation Trade-Off in Resource-Constrained Edge Inference](https://mlsanity.com/paper/2006.02166/) (2020)
- [MoETuner: Optimized Mixture of Expert Serving with Balanced Expert Placement and Token Routing](https://mlsanity.com/paper/2502.06643/) (2025)
- [WDMoE: Wireless Distributed Mixture of Experts for Large Language Models](https://mlsanity.com/paper/2411.06681/) (2024)
- [Spectrum Breathing: Protecting Over-the-Air Federated Learning Against Interference](https://mlsanity.com/paper/2305.05933/) (2023)
- [Space-ground Fluid AI for 6G Edge Intelligence](https://mlsanity.com/paper/2411.15845/) (2024)
- [Optimizing Mixture-of-Experts Inference Time Combining Model Deployment and Communication Scheduling](https://mlsanity.com/paper/2410.17043/) (2024)
- [SlimCaching: Edge Caching of Mixture-of-Experts for Distributed Inference](https://mlsanity.com/paper/2507.06567/) (2025)
- [Exploring GPU-to-GPU Communication: Insights into Supercomputer Interconnects](https://mlsanity.com/paper/2408.14090/) (2024)
- [Efficient Pre-Training of LLMs via Topology-Aware Communication Alignment on More Than 9600 GPUs](https://mlsanity.com/paper/2509.15940/) (2025)
- [Revisiting Outage for Edge Inference Systems](https://mlsanity.com/paper/2504.03686/) (2025)
- [Satellite Edge Artificial Intelligence with Large Models: Architectures and Technologies](https://mlsanity.com/paper/2504.01676/) (2025)
- [Towards a future space-based, highly scalable AI infrastructure system design](https://mlsanity.com/paper/2511.19468/) (2025)
- [Optimal Batch-Size Control for Low-Latency Federated Learning with Device Heterogeneity](https://mlsanity.com/paper/2507.15601/) (2025)
- [Cluster Topology-Driven Placement of Experts Reduces Network Traffic in MoE Inference](https://mlsanity.com/paper/2508.09229/) (2025)

## Built on by (most cited first, 3 of 3)

- [Multi-SPIN: Multi-Access Speculative Inference for Cooperative Token Generation at the Edge](https://mlsanity.com/paper/2606.04581/) (2026)
- [Space Generative AI with Solar Energy Harvesting](https://mlsanity.com/paper/2609.01062/) (2026)
- [SpaceDiffusion: Over-the-Orbit Diffusion for Space Generate-and-Forward Communications](https://mlsanity.com/paper/2609.20899/) (2026)

## Abstract (arXiv)

Leveraging continuous solar energy harvesting at high efficiency, space data centers are envisioned as a promising platform for executing energy-intensive large language models (LLMs). Recognizing this advantage, space and AI conglomerates (e.g., SpaceX, Google) are actively investing in this vision. One key challenge, however, is the efficient distributed deployment of a large-scale LLM in a satellite network due to the limited onboard computing and communication resources. This gives rise to a placement problem that involves partitioning and mapping model components to satellites such that the fundamentally different model architecture and network topology can be reconciled to ensure low-latency token generation. To address this problem, we present the Space Network of Mixture-of-Experts (SpaceMoE) framework targeting the distributed execution of a popular mixture-of-experts (MoE) model in space. The proposed placement strategies are two-level: (1) layer placement, which assigns MoE layers to satellite subnets; and (2) intra-layer expert placement, which assigns individual experts to satellites associated with the same layer/subnet. For layer placement, we exploit the ring-like communication pattern of autoregressive inference to partition the satellite constellation along the orbiting direction into subnets arranged on a ring, each hosting one MoE layer. Based on this architecture, we formulate and solve an optimization problem for intra-layer expert placement to map experts with heterogeneous activation probabilities onto satellites. The derived strategy reveals an intuitive principle: a frequently activated expert should be mapped to a satellite on a routing path with low expected latency. Experiments over a thousand-satellite constellation show that SpaceMoE achieves at least a threefold latency reduction compared with conventional random and ablation-based placement strategies.