# ELMoE-3D: Leveraging Intrinsic Elasticity of MoE for Hybrid-Bonding-Enabled Self-Speculative Decoding in On-Premises Serving

arXiv: https://arxiv.org/abs/2604.14626 · HTML: https://mlsanity.com/paper/2604.14626/

## 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 37 of its 66 references that are in the map.
- First posted on arXiv 16 Apr 2026.

## 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 / [Speculative decoding](https://mlsanity.com/inference/speculative-decoding/)

## Builds on (most cited first, 30 of 37)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://mlsanity.com/paper/2401.15077/) (2024)
- [EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees](https://mlsanity.com/paper/2406.16858/) (2024)
- [EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test](https://mlsanity.com/paper/2503.01840/) (2025)
- [LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding](https://mlsanity.com/paper/2404.16710/) (2024)
- [Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Networks](https://mlsanity.com/paper/1712.01507/) (2017)
- [Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference](https://mlsanity.com/paper/2308.12066/) (2023)
- [MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs](https://mlsanity.com/paper/2411.11217/) (2024)
- [Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs](https://mlsanity.com/paper/2402.10517/) (2024)
- [NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing](https://mlsanity.com/paper/2403.00579/) (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)
- [Speculative Decoding via Early-exiting for Faster LLM Inference with Thompson Sampling Control Mechanism](https://mlsanity.com/paper/2406.03853/) (2024)
- [Ramulator 2.0: A Modern, Modular, and Extensible DRAM Simulator](https://mlsanity.com/paper/2308.11030/) (2023)
- [NestQuant: Nested Lattice Quantization for Matrix Products and LLMs](https://mlsanity.com/paper/2502.09720/) (2025)
- [Direct Alignment of Draft Model for Speculative Decoding with Chat-Fine-Tuned LLMs](https://mlsanity.com/paper/2403.00858/) (2024)
- [MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE](https://mlsanity.com/paper/2505.19645/) (2025)
- [Mixture of Cache-Conditional Experts for Efficient Mobile Device Inference](https://mlsanity.com/paper/2412.00099/) (2024)
- [Matryoshka Quantization](https://mlsanity.com/paper/2502.06786/) (2025)
- [Utility-Driven Speculative Decoding for Mixture-of-Experts](https://mlsanity.com/paper/2506.20675/) (2025)
- [SP-MoE: Speculative Decoding and Prefetching for Accelerating MoE-based Model Inference](https://mlsanity.com/paper/2510.10302/) (2025)
- [MoE-Spec: Expert Budgeting for Efficient Speculative Decoding](https://mlsanity.com/paper/2602.16052/) (2026)
- [MoE-SpeQ: Speculative Quantized Decoding with Proactive Expert Prefetching and Offloading for Mixture-of-Experts](https://mlsanity.com/paper/2511.14102/) (2025)
- [ML-SpecQD: Multi-Level Speculative Decoding with Quantized Drafts](https://mlsanity.com/paper/2503.13565/) (2025)
- [LP-Spec: Leveraging LPDDR PIM for Efficient LLM Mobile Speculative Inference with Architecture-Dataflow Co-Optimization](https://mlsanity.com/paper/2508.07227/) (2025)
- [AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs](https://mlsanity.com/paper/2510.10467/) (2025)

## Abstract (arXiv)

Mixture-of-Experts (MoE) models have become the dominant architecture for large-scale language models, yet on-premises serving remains fundamentally memory-bound as batching turns sparse per-token compute into dense memory activation. Memory-centric architectures (PIM, NMP) improve bandwidth but leave compute underutilized under MoE's low arithmetic intensity at high batch sizes. Speculative decoding (SD) trades idle compute for fewer target invocations, yet verification must load experts even for rejected tokens, severely limiting its benefit in MoE especially at low batch sizes. We propose ELMoE-3D, a hybrid-bonding (HB)-based HW-SW co-designed framework that unifies cache-based acceleration and speculative decoding to offer overall speedup across batch sizes. We identify two intrinsic elasticity axes of MoE-expert and bit-and jointly scale them to construct Elastic Self-Speculative Decoding (Elastic-SD), which serves as both an expert cache and a strongly aligned self-draft model accelerated by high HB bandwidth. Our LSB-augmented bit-sliced architecture exploits inherent redundancy in bit-slice representations to natively support bit-nested execution. On our 3D-stacked hardware, ELMoE-3D achieves an average 6.6× speedup and 4.4× energy efficiency gain over naive MoE serving on xPU across batch sizes 1-16, and delivers 2.2× speedup and 1.4× energy efficiency gain over the best-performing prior accelerator baseline.