# HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference

arXiv: https://arxiv.org/abs/2411.01433 · HTML: https://mlsanity.com/paper/2411.01433/

## Key facts

- Cited by 55 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 37 of its 58 references that are in the map.
- First posted on arXiv 3 Nov 2024.

## 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 37)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes](https://mlsanity.com/paper/2306.13649/) (2023)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [LLM-Pruner: On the Structural Pruning of Large Language Models](https://mlsanity.com/paper/2305.11627/) (2023)
- [TinyLlama: An Open-Source Small Language Model](https://mlsanity.com/paper/2401.02385/) (2024)
- [ShortGPT: Layers in Large Language Models are More Redundant Than You Expect](https://mlsanity.com/paper/2403.03853/) (2024)
- [Learning Factored Representations in a Deep Mixture of Experts](https://mlsanity.com/paper/1312.4314/) (2013)
- [ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learning](https://mlsanity.com/paper/2104.07857/) (2021)
- [Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time](https://mlsanity.com/paper/2310.17157/) (2023)
- [SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression](https://mlsanity.com/paper/2403.07378/) (2024)
- [PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU](https://mlsanity.com/paper/2312.12456/) (2023)
- [BitNet: Scaling 1-bit Transformers for Large Language Models](https://mlsanity.com/paper/2310.11453/) (2023)
- [MobileVLM V2: Faster and Stronger Baseline for Vision Language Model](https://mlsanity.com/paper/2402.03766/) (2024)
- [ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models](https://mlsanity.com/paper/2312.05821/) (2023)
- [MiniLLM: On-Policy Distillation of Large Language Models](https://mlsanity.com/paper/2306.08543/) (2023)
- [Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy](https://mlsanity.com/paper/2310.01334/) (2023)
- [LoSparse: Structured Compression of Large Language Models based on Low-Rank and Sparse Approximation](https://mlsanity.com/paper/2306.11222/) (2023)
- [PowerInfer-2: Fast Large Language Model Inference on a Smartphone](https://mlsanity.com/paper/2406.06282/) (2024)
- [Fast Inference of Mixture-of-Experts Language Models with Offloading](https://mlsanity.com/paper/2312.17238/) (2023)
- [Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods](https://mlsanity.com/paper/2402.02834/) (2024)
- [Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models](https://mlsanity.com/paper/2402.07033/) (2024)

## Built on by (most cited first, 30 of 55)

- [A Survey on Inference Optimization Techniques for Mixture of Experts Models](https://mlsanity.com/paper/2412.14219/) (2024)
- [Advancing Expert Specialization for Better MoE](https://mlsanity.com/paper/2505.22323/) (2025)
- [Delta Decompression for MoE-based LLMs Compression](https://mlsanity.com/paper/2502.17298/) (2025)
- [MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design](https://mlsanity.com/paper/2505.05799/) (2025)
- [A Survey on Large Language Models for Communication, Network, and Service Management: Application Insights, Challenges, and Future Directions](https://mlsanity.com/paper/2412.19823/) (2024)
- [Taming Latency-Memory Trade-Off in MoE-Based LLM Serving via Fine-Grained Expert Offloading](https://mlsanity.com/paper/2502.05370/) (2025)
- [MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE](https://mlsanity.com/paper/2505.19645/) (2025)
- [HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference](https://mlsanity.com/paper/2504.05897/) (2025)
- [Mixture of Cache-Conditional Experts for Efficient Mobile Device Inference](https://mlsanity.com/paper/2412.00099/) (2024)
- [SP-MoE: Speculative Decoding and Prefetching for Accelerating MoE-based Model Inference](https://mlsanity.com/paper/2510.10302/) (2025)
- [MoE-SpeQ: Speculative Quantized Decoding with Proactive Expert Prefetching and Offloading for Mixture-of-Experts](https://mlsanity.com/paper/2511.14102/) (2025)
- [FloE: On-the-Fly MoE Inference on Memory-constrained GPU](https://mlsanity.com/paper/2505.05950/) (2025)
- [Accelerating Mixture-of-Expert Inference with Adaptive Expert Split Mechanism](https://mlsanity.com/paper/2509.08342/) (2025)
- [Not All Models Suit Expert Offloading: On Local Routing Consistency of Mixture-of-Expert Models](https://mlsanity.com/paper/2505.16056/) (2025)
- [Dynamic Expert Quantization for Scalable Mixture-of-Experts Inference](https://mlsanity.com/paper/2511.15015/) (2025)
- [Effective MoE-based LLM Compression by Exploiting Heterogeneous Inter-Group Experts Routing Frequency and Information Density](https://mlsanity.com/paper/2602.09316/) (2026)
- [MoE-Gen: High-Throughput MoE Inference on a Single GPU with Module-Based Batching](https://mlsanity.com/paper/2503.09716/) (2025)
- [Mixed-Precision Quantization for Language Models: Techniques and Prospects](https://mlsanity.com/paper/2510.16805/) (2025)
- [ExpertFlow: Adaptive Expert Scheduling and Memory Coordination for Efficient MoE Inference](https://mlsanity.com/paper/2510.26730/) (2025)
- [MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios](https://mlsanity.com/paper/2603.09983/) (2026)
- [Pre-Attention Expert Prediction and Prefetching for Mixture-of-Experts Large Language Models](https://mlsanity.com/paper/2511.10676/) (2025)
- [PCR: A Prefetch-Enhanced Cache Reuse System for Low-Latency RAG Serving](https://mlsanity.com/paper/2603.23049/) (2026)
- [Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression](https://mlsanity.com/paper/2510.02345/) (2025)
- [SliceMoE: Bit-Sliced Expert Caching under Miss-Rate Constraints for Efficient MoE Inference](https://mlsanity.com/paper/2512.12990/) (2025)
- [Bandwidth-Efficient Adaptive Mixture-of-Experts via Low-Rank Compensation](https://mlsanity.com/paper/2512.17073/) (2025)
- [ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference](https://mlsanity.com/paper/2605.27081/) (2026)
- [FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution](https://mlsanity.com/paper/2608.16157/) (2026)
- [CoMoE: Collaborative Optimization of Expert Aggregation and Offloading for MoE-based LLMs at Edge](https://mlsanity.com/paper/2508.09208/) (2025)
- [Context-Aware Mixture-of-Experts Inference on CXL-Enabled GPU-NDP Systems](https://mlsanity.com/paper/2512.04476/) (2025)
- [Remoe: Towards Efficient and Low-Cost MoE Inference in Serverless Computing](https://mlsanity.com/paper/2512.18674/) (2025)

## Abstract (arXiv)

The Mixture-of-Experts (MoE) architecture has demonstrated significant advantages in the era of Large Language Models (LLMs), offering enhanced capabilities with reduced inference costs. However, deploying MoE-based LLMs on memoryconstrained edge devices remains challenging due to their substantial memory requirements. While existing expertoffloading methods alleviate the memory requirements, they often incur significant expert-loading costs or compromise model accuracy. We present HOBBIT, a mixed precision expert offloading system to enable flexible and efficient MoE inference. Our key insight is that dynamically replacing less critical cache-miss experts with low precision versions can substantially reduce expert-loading latency while preserving model accuracy. HOBBIT introduces three innovative techniques that map the natural hierarchy of MoE computation: (1) a token-level dynamic expert loading mechanism, (2) a layer-level adaptive expert prefetching technique, and (3) a sequence-level multidimensional expert caching policy. These innovations fully leverage the benefits of mixedprecision expert inference. By implementing HOBBIT on top of the renowned LLM inference framework Llama.cpp, we evaluate its performance across different edge devices with representative MoE models. The results demonstrate that HOBBIT achieves up to a 9.93x speedup in decoding compared to state-of-the-art MoE offloading systems.