# FlexInfer: Breaking Memory Constraint via Flexible and Efficient Offloading for On-Device LLM Inference

arXiv: https://arxiv.org/abs/2503.03777 · HTML: https://mlsanity.com/paper/2503.03777/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 51 references that are in the map.
- First posted on arXiv 4 Mar 2025.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://mlsanity.com/paper/2305.02301/) (2023)
- [TinyLlama: An Open-Source Small Language Model](https://mlsanity.com/paper/2401.02385/) (2024)
- [ZeRO-Offload: Democratizing Billion-Scale Model Training](https://mlsanity.com/paper/2101.06840/) (2021)
- [Atom: Low-bit Quantization for Efficient and Accurate LLM Serving](https://mlsanity.com/paper/2310.19102/) (2023)
- [Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time](https://mlsanity.com/paper/2310.17157/) (2023)
- [PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU](https://mlsanity.com/paper/2312.12456/) (2023)
- [LLM in a flash: Efficient Large Language Model Inference with Limited Memory](https://mlsanity.com/paper/2312.11514/) (2023)
- [PowerInfer-2: Fast Large Language Model Inference on a Smartphone](https://mlsanity.com/paper/2406.06282/) (2024)
- [Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization](https://mlsanity.com/paper/1910.02653/) (2019)
- [OneBit: Towards Extremely Low-bit Large Language Models](https://mlsanity.com/paper/2402.11295/) (2024)
- [LLM-Rec: Personalized Recommendation via Prompting Large Language Models](https://mlsanity.com/paper/2307.15780/) (2023)
- [An empirical study of LLaMA3 quantization: from LLMs to MLLMs](https://mlsanity.com/paper/2404.14047/) (2024)
- [LLMCad: Fast and Scalable On-device Large Language Model Inference](https://mlsanity.com/paper/2309.04255/) (2023)
- [What is the Role of Small Models in the LLM Era: A Survey](https://mlsanity.com/paper/2409.06857/) (2024)
- [POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging](https://mlsanity.com/paper/2207.07697/) (2022)
- [CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification](https://mlsanity.com/paper/2409.01366/) (2024)
- [When Compression Meets Model Compression: Memory-Efficient Double Compression for Large Language Models](https://mlsanity.com/paper/2502.15443/) (2025)
- [EvoP: Robust LLM Inference via Evolutionary Pruning](https://mlsanity.com/paper/2502.14910/) (2025)

## Built on by (most cited first, 4 of 4)

- [LayerScope: Predictive Cross-Layer Scheduling for Efficient Multi-Batch MoE Inference on Legacy Servers](https://mlsanity.com/paper/2509.23638/) (2025)
- [RAGDoll: Efficient Offloading-based Online RAG System on a Single GPU](https://mlsanity.com/paper/2504.15302/) (2025)
- [Characterizing State Space Model and Hybrid Language Model Performance with Long Context](https://mlsanity.com/paper/2507.12442/) (2025)
- [JustFit: Just-in-Time State Management for Local LLM Serving](https://mlsanity.com/paper/2609.17475/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) face challenges for on-device inference due to high memory demands. Traditional methods to reduce memory usage often compromise performance and lack adaptability. We propose FlexInfer, an optimized offloading framework for on-device inference, addressing these issues with techniques like asynchronous prefetching, balanced memory locking, and flexible tensor preservation. These strategies enhance memory efficiency and mitigate I/O bottlenecks, ensuring high performance within user-specified resource constraints. Experiments demonstrate that FlexInfer significantly improves throughput under limited resources, achieving up to 12.5 times better performance than existing methods and facilitating the deployment of large models on resource-constrained devices.