# A Scheduling Framework for Efficient MoE Inference on Edge GPU-NDP Systems

arXiv: https://arxiv.org/abs/2601.03992 · HTML: https://mlsanity.com/paper/2601.03992/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Efficient MoE training and inference systems, one of 12 directions in Mixture-of-experts.
- Builds on 30 of its 43 references that are in the map.
- First posted on arXiv 7 Jan 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, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [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)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [A Survey on Mixture of Experts in Large Language Models](https://mlsanity.com/paper/2407.06204/) (2024)
- [Fast Inference of Mixture-of-Experts Language Models with Offloading](https://mlsanity.com/paper/2312.17238/) (2023)
- [MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs](https://mlsanity.com/paper/2411.11217/) (2024)
- [Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models](https://mlsanity.com/paper/2402.07033/) (2024)
- [RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing](https://mlsanity.com/paper/1912.12953/) (2019)
- [TensorDIMM: A Practical Near-Memory Processing Architecture for Embeddings and Tensor Operations in Deep Learning](https://mlsanity.com/paper/1908.03072/) (2019)
- [Duplex: A Device for Large Language Models with Mixture of Experts, Grouped Query Attention, and Continuous Batching](https://mlsanity.com/paper/2409.01141/) (2024)
- [Phi-3 Safety Post-Training: Aligning Language Models with a "Break-Fix" Cycle](https://mlsanity.com/paper/2407.13833/) (2024)
- [Ramulator 2.0: A Modern, Modular, and Extensible DRAM Simulator](https://mlsanity.com/paper/2308.11030/) (2023)
- [Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipeline](https://mlsanity.com/paper/2502.06888/) (2025)
- [DAOP: Data-Aware Offloading and Predictive Pre-Calculation for Efficient MoE Inference](https://mlsanity.com/paper/2501.10375/) (2024)
- [A Precision-Scalable RISC-V DNN Processor with On-Device Learning Capability at the Extreme Edge](https://mlsanity.com/paper/2309.08186/) (2023)
- [MoNDE: Mixture of Near-Data Experts for Large-Scale Sparse Models](https://mlsanity.com/paper/2405.18832/) (2024)
- [Anda: Unlocking Efficient LLM Inference with a Variable-Length Grouped Activation Data Format](https://mlsanity.com/paper/2411.15982/) (2024)
- [LP-Spec: Leveraging LPDDR PIM for Efficient LLM Mobile Speculative Inference with Architecture-Dataflow Co-Optimization](https://mlsanity.com/paper/2508.07227/) (2025)
- [Make LLM Inference Affordable to Everyone: Augmenting GPU Memory with NDP-DIMM](https://mlsanity.com/paper/2502.16963/) (2025)
- [BRAMAC: Compute-in-BRAM Architectures for Multiply-Accumulate on FPGAs](https://mlsanity.com/paper/2304.03974/) (2023)
- [Co-Designing Binarized Transformer and Hardware Accelerator for Efficient End-to-End Edge Deployment](https://mlsanity.com/paper/2407.12070/) (2024)
- [Near-Memory Parallel Indexing and Coalescing: Enabling Highly Efficient Indirect Access for SpMV](https://mlsanity.com/paper/2311.10378/) (2023)
- [NDPage: Efficient Address Translation for Near-Data Processing Architectures via Tailored Page Table](https://mlsanity.com/paper/2502.14220/) (2025)

## Abstract (arXiv)

Mixture-of-Experts (MoE) models facilitate edge deployment by decoupling model capacity from active computation, yet their large memory footprint drives the need for GPU systems with near-data processing (NDP) capabilities that offload experts to dedicated processing units. However, deploying MoE models on such edge-based GPU-NDP systems faces three critical challenges: 1) severe load imbalance across NDP units due to non-uniform expert selection and expert parallelism, 2) insufficient GPU utilization during expert computation within NDP units, and 3) extensive data pre-profiling necessitated by unpredictable expert activation patterns for pre-fetching. To address these challenges, this paper proposes an efficient inference framework featuring three key optimizations. First, the underexplored tensor parallelism in MoE inference is exploited to partition and compute large expert parameters across multiple NDP units simultaneously towards edge low-batch scenarios. Second, a load-balancing-aware scheduling algorithm distributes expert computations across NDP units and GPU to maximize resource utilization. Third, a dataset-free pre-fetching strategy proactively loads frequently accessed experts to minimize activation delays. Experimental results show that our framework enables GPU-NDP systems to achieve 2.41x on average and up to 2.56x speedup in end-to-end latency compared to state-of-the-art approaches, significantly enhancing MoE inference efficiency in resource-constrained environments.