# A3D-MoE: Acceleration of Large Language Models with Mixture of Experts via 3D Heterogeneous Integration

arXiv: https://arxiv.org/abs/2507.19142 · HTML: https://mlsanity.com/paper/2507.19142/

## Key facts

- Cited by 2 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 14 of its 28 references that are in the map.
- First posted on arXiv 25 Jul 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, 14 of 14)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [Large Language Models: A Survey](https://mlsanity.com/paper/2402.06196/) (2024)
- [OLMoE: Open Mixture-of-Experts Language Models](https://mlsanity.com/paper/2409.02060/) (2024)
- [A Survey on Mixture of Experts in Large Language Models](https://mlsanity.com/paper/2407.06204/) (2024)
- [Scaling Laws for Fine-Grained Mixture of Experts](https://mlsanity.com/paper/2402.07871/) (2024)
- [Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers](https://mlsanity.com/paper/2002.11794/) (2020)
- [NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing](https://mlsanity.com/paper/2403.00579/) (2024)
- [AdapMoE: Adaptive Sensitivity-based Expert Gating and Management for Efficient MoE Inference](https://mlsanity.com/paper/2408.10284/) (2024)
- [Duplex: A Device for Large Language Models with Mixture of Experts, Grouped Query Attention, and Continuous Batching](https://mlsanity.com/paper/2409.01141/) (2024)
- [Ramulator 2.0: A Modern, Modular, and Extensible DRAM Simulator](https://mlsanity.com/paper/2308.11030/) (2023)

## Built on by (most cited first, 2 of 2)

- [ThAME: 3D Memory-Enabled Heterogeneous Accelerator for LLM Mixture of Experts](https://mlsanity.com/paper/2607.17074/) (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)

## Abstract (arXiv)

Conventional large language models (LLMs) are equipped with dozens of GB to TB of model parameters, making inference highly energy-intensive and costly as all the weights need to be loaded to onboard processing elements during computation. Recently, the Mixture-of-Experts (MoE) architecture has emerged as an efficient alternative, promising efficient inference with less activated weights per token. Nevertheless, fine-grained MoE-based LLMs face several challenges: 1) Variable workloads during runtime create arbitrary GEMV-GEMM ratios that reduce hardware utilization, 2) Traditional MoE-based scheduling for LLM serving cannot fuse attention operations with MoE operations, leading to increased latency and decreased hardware utilization, and 3) Despite being more efficient than conventional LLMs, loading experts from DRAM still consumes significant energy and requires substantial DRAM bandwidth. Addressing these challenges, we propose: 1) A3D-MoE, a 3D Heterogeneous Integration system that employs state-of-the-art vertical integration technology to significantly enhance memory bandwidth while reducing Network-on-Chip (NoC) overhead and energy consumption. 2) A 3D-Adaptive GEMV-GEMM-ratio systolic array with V-Cache efficient data reuse and a novel unified 3D dataflow to solve the problem of reduced hardware utilization caused by arbitrary GEMV-GEMM ratios from different workloads, 3) A Hardware resource-aware operation fusion scheduler that fuses attention operations with MoE operations to enhance hardware performance, and 4) MoE Score-Aware HBM access reduction with even-odd expert placement that reduces DRAM access and bandwidth requirements. Our evaluation results indicate that A3D-MoE delivers significant performance enhancements, reducing latency by a factor of 1.8x to 2x and energy consumption by 2x to 4x, while improving throughput by 1.44x to 1.8x compared to the state-of-the-art.