# Duplex: A Device for Large Language Models with Mixture of Experts, Grouped Query Attention, and Continuous Batching

arXiv: https://arxiv.org/abs/2409.01141 · HTML: https://mlsanity.com/paper/2409.01141/

## Key facts

- Cited by 34 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 26 of its 65 references that are in the map.
- First posted on arXiv 2 Sep 2024.

## Placed in

- Mixture-of-experts / [Efficient MoE training and inference systems](https://mlsanity.com/moe/efficient-moe-training-and-inference-systems/)
- Efficient LLM inference and serving / [Diffusion LLM and MoE inference](https://mlsanity.com/inference/diffusion-llm-and-moe-inference/)

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [GLaM: Efficient Scaling of Language Models with Mixture-of-Experts](https://mlsanity.com/paper/2112.06905/) (2021)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale](https://mlsanity.com/paper/2201.05596/) (2022)
- [SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning](https://mlsanity.com/paper/2012.09852/) (2020)
- [Efficient Large Scale Language Modeling with Mixtures of Experts](https://mlsanity.com/paper/2112.10684/) (2021)
- [GOBO: Quantizing Attention-Based NLP Models for Low Latency and Energy Efficient Inference](https://mlsanity.com/paper/2005.03842/) (2020)
- [A3: Accelerating Attention Mechanisms in Neural Networks with Approximation](https://mlsanity.com/paper/2002.10941/) (2020)
- [OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization](https://mlsanity.com/paper/2304.07493/) (2023)
- [NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing](https://mlsanity.com/paper/2403.00579/) (2024)
- [DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation](https://mlsanity.com/paper/2209.10797/) (2022)
- [FLAT: An Optimized Dataflow for Mitigating Attention Bottlenecks](https://mlsanity.com/paper/2107.06419/) (2021)
- [Towards MoE Deployment: Mitigating Inefficiencies in Mixture-of-Expert (MoE) Inference](https://mlsanity.com/paper/2303.06182/) (2023)
- [Adaptable Butterfly Accelerator for Attention-based NNs via Hardware and Algorithm Co-design](https://mlsanity.com/paper/2209.09570/) (2022)
- [Ramulator 2.0: A Modern, Modular, and Extensible DRAM Simulator](https://mlsanity.com/paper/2308.11030/) (2023)
- [An Algorithm-Hardware Co-Optimized Framework for Accelerating N:M Sparse Transformers](https://mlsanity.com/paper/2208.06118/) (2022)
- [Mokey: Enabling Narrow Fixed-Point Inference for Out-of-the-Box Floating-Point Transformer Models](https://mlsanity.com/paper/2203.12758/) (2022)
- [Accelerating Attention through Gradient-Based Learned Runtime Pruning](https://mlsanity.com/paper/2204.03227/) (2022)

## Built on by (most cited first, 30 of 34)

- [A Survey on Inference Optimization Techniques for Mixture of Experts Models](https://mlsanity.com/paper/2412.14219/) (2024)
- [Challenges and Research Directions for Large Language Model Inference Hardware](https://mlsanity.com/paper/2601.05047/) (2026)
- [Stratum: System-Hardware Co-Design with Tiered Monolithic 3D-Stackable DRAM for Efficient MoE Serving](https://mlsanity.com/paper/2510.05245/) (2025)
- [Chameleon: Adaptive Caching and Scheduling for Many-Adapter LLM Inference Environments](https://mlsanity.com/paper/2411.17741/) (2024)
- [Predicting LLM Output Length via Entropy-Guided Representations](https://mlsanity.com/paper/2602.11812/) (2026)
- [LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure](https://mlsanity.com/paper/2602.23036/) (2026)
- [Patterns behind Chaos: Forecasting Data Movement for Efficient Large-Scale MoE LLM Inference](https://mlsanity.com/paper/2510.05497/) (2025)
- [LLMServingSim2.0: A Unified Simulator for Heterogeneous Hardware and Serving Techniques in LLM Infrastructure](https://mlsanity.com/paper/2511.07229/) (2025)
- [HPU: High-Bandwidth Processing Unit for Scalable, Cost-effective LLM Inference via GPU Co-processing](https://mlsanity.com/paper/2504.16112/) (2025)
- [CHIME: A Case for Efficient Long-Context Attention-FC Disaggregated Inference with DIMM-PIM](https://mlsanity.com/paper/2504.17584/) (2025)
- [A Cost-Effective Near-Storage Processing Solution for Offline Inference of Long-Context LLMs](https://mlsanity.com/paper/2502.09921/) (2025)
- [Rethinking LLM Inference Bottlenecks: Insights from Latent Attention and Mixture-of-Experts](https://mlsanity.com/paper/2507.15465/) (2025)
- [SSD Offloading for LLM Mixture-of-Experts Weights Considered Harmful in Energy Efficiency](https://mlsanity.com/paper/2508.06978/) (2025)
- [SpecMoE: A Fast and Efficient Mixture-of-Experts Inference via Self-Assisted Speculative Decoding](https://mlsanity.com/paper/2604.10152/) (2026)
- [P3-LLM: An Integrated NPU-PIM Accelerator for Edge LLM Inference Using Hybrid Numerical Formats](https://mlsanity.com/paper/2511.06838/) (2025)
- [Bandwidth-Efficient Adaptive Mixture-of-Experts via Low-Rank Compensation](https://mlsanity.com/paper/2512.17073/) (2025)
- [A3D-MoE: Acceleration of Large Language Models with Mixture of Experts via 3D Heterogeneous Integration](https://mlsanity.com/paper/2507.19142/) (2025)
- [Context-Aware Mixture-of-Experts Inference on CXL-Enabled GPU-NDP Systems](https://mlsanity.com/paper/2512.04476/) (2025)
- [Cocoon: A System Architecture for Differentially Private Training with Correlated Noises](https://mlsanity.com/paper/2510.07304/) (2025)
- [LOCALUT: Harnessing Capacity-Computation Tradeoffs for LUT-Based Inference in DRAM-PIM](https://mlsanity.com/paper/2604.04523/) (2026)
- [A Scheduling Framework for Efficient MoE Inference on Edge GPU-NDP Systems](https://mlsanity.com/paper/2601.03992/) (2026)
- [Hardware-Software Co-design for 3D-DRAM-based LLM Serving Accelerator](https://mlsanity.com/paper/2603.04797/) (2026)
- [ELMoE-3D: Leveraging Intrinsic Elasticity of MoE for Hybrid-Bonding-Enabled Self-Speculative Decoding in On-Premises Serving](https://mlsanity.com/paper/2604.14626/) (2026)
- [AMMA: A Multi-Chiplet Memory-Centric Architecture for Low-Latency 1M Context Attention Serving](https://mlsanity.com/paper/2604.26103/) (2026)
- [TokenStack: A Heterogeneous HBM-PIM Architecture and Runtime for Efficient LLM Inference](https://mlsanity.com/paper/2605.05639/) (2026)
- [Sieve: Dynamic Expert-Aware PIM Acceleration for Evolving Mixture-of-Experts Models](https://mlsanity.com/paper/2605.11277/) (2026)
- [Cassandra: Enabling Reasoning LLMs at Edge via Self-Speculative Decoding](https://mlsanity.com/paper/2605.26558/) (2026)
- [Beyond Prefill-Decode Disaggregation: Dissecting LLM Inference for Heterogeneous Platforms via Dynamic Operator Scheduling](https://mlsanity.com/paper/2607.25498/) (2026)
- [Heterogeneous LLM Serving with General-Purpose Processing-Near-Memory for Retrieval-Based Sparse Attention](https://mlsanity.com/paper/2608.03555/) (2026)
- [EdgeXpert: An Edge Device for Memory-Efficient LLM Inference with Mixture-of-Experts and Speculative Decoding](https://mlsanity.com/paper/2608.05303/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have emerged due to their capability to generate high-quality content across diverse contexts. To reduce their explosively increasing demands for computing resources, a mixture of experts (MoE) has emerged. The MoE layer enables exploiting a huge number of parameters with less computation. Applying state-of-the-art continuous batching increases throughput; however, it leads to frequent DRAM access in the MoE and attention layers. We observe that conventional computing devices have limitations when processing the MoE and attention layers, which dominate the total execution time and exhibit low arithmetic intensity (Op/B). Processing MoE layers only with devices targeting low-Op/B such as processing-in-memory (PIM) architectures is challenging due to the fluctuating Op/B in the MoE layer caused by continuous batching. To address these challenges, we propose Duplex, which comprises xPU tailored for high-Op/B and Logic-PIM to effectively perform low-Op/B operation within a single device. Duplex selects the most suitable processor based on the Op/B of each layer within LLMs. As the Op/B of the MoE layer is at least 1 and that of the attention layer has a value of 4-8 for grouped query attention, prior PIM architectures are not efficient, which place processing units inside DRAM dies and only target extremely low-Op/B (under one) operations. Based on recent trends, Logic-PIM adds more through-silicon vias (TSVs) to enable high-bandwidth communication between the DRAM die and the logic die and place powerful processing units on the logic die, which is best suited for handling low-Op/B operations ranging from few to a few dozens. To maximally utilize the xPU and Logic-PIM, we propose expert and attention co-processing.