MobiZO: Enabling Efficient LLM Fine-Tuning at the Edge via Inference Engines

• URL: http://arxiv.org/abs/2409.15520v3
• Date: Sat, 20 Sep 2025 21:59:16 GMT
• Title: MobiZO: Enabling Efficient LLM Fine-Tuning at the Edge via Inference Engines
• Authors: Lei Gao, Amir Ziashahabi, Yue Niu, Salman Avestimehr, Murali Annavaram,
• Abstract summary: We introduce MobiZO, a resource-efficient fine-tuning framework for Large Language Models (LLMs) specifically designed for edge devices.<n>We show that MobiZO achieves substantial runtime speedups and memory savings while improving fine-tuning accuracy.<n> Experiments demonstrate that MobiZO achieves substantial runtime speedups and memory savings while improving fine-tuning accuracy.
• Score: 28.18421624702502
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Large Language Models (LLMs) are currently pre-trained and fine-tuned on large cloud servers. The next frontier is LLM personalization, where a foundation model can be fine-tuned with user/task-specific data. Given the sensitive nature of such private data, it is desirable to fine-tune these models on edge devices to improve user trust. However, fine-tuning on resource-constrained edge devices presents significant challenges due to substantial memory and computational demands, as well as limited infrastructure support. We observe that inference engines (e.g., ExecuTorch) can be repurposed for fine-tuning by leveraging zeroth-order (ZO) optimization, which uses multiple forward passes to approximate gradients. While promising, direct application of ZO methods on edge devices is inefficient due to the high computational cost of multiple forward passes required for accurate gradient estimation, and their deployment has been largely unexplored in practice. We introduce MobiZO, a resource-efficient fine-tuning framework for LLMs specifically designed for edge devices. MobiZO combines three key innovations: (1) a parallelized randomized gradient estimator that employs both outer-loop and inner-loop parallelism to eliminate sequential forward passes, (2) a specialized Multi-Perturbed LoRA (MP-LoRA) module that enables efficient realization of both inner and outer loop parallelism, and (3) a seamless integration with ExecuTorch for on-device training, requiring no modifications to the runtime. Experiments demonstrate that MobiZO achieves substantial runtime speedups and memory savings while improving fine-tuning accuracy, paving the way for practical deployment of LLMs in real-time, on-device applications.

Related papers

• AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering [52.67783579040657]
  AceGRPO is a machine learning system that prioritizes tasks at the agent's learning frontier to maximize learning efficiency.<n>Our trained Ace-30B model achieves a 100% valid submission rate on MLE-Bench-Lite, approaches the performance of proprietary frontier models, and outperforms larger open-source baselines.
  arXiv  Detail & Related papers  (2026-02-08T10:55:03Z)
• RollArt: Scaling Agentic RL Training via Disaggregated Infrastructure [49.88201789074532]
  Agentic Reinforcement Learning (RL) enables Large Language Models (LLMs) to perform autonomous decision-making and long-term planning.<n>We present RollArc, a distributed system designed to maximize throughput for multi-task agentic RL on disaggregated infrastructure.
  arXiv  Detail & Related papers  (2025-12-27T11:14:23Z)
• From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices [3.4233698915405544]
  This paper benchmarks and analyzes popular PEFT methods on convolutional architectures typically deployed in resource-constrained edge environments.<n>We find that the evaluated PEFT methods are only half as memory-efficient when applied to depthwise-separable convolution architectures.
  arXiv  Detail & Related papers  (2025-07-31T13:23:21Z)
• Gradient-based Fine-Tuning through Pre-trained Model Regularization [20.823624386591902]
  We propose an efficient gradient-based and regularized fine-tuning method (GRFT) that updates the rows or columns of the weight matrix.<n> GRFT achieves state-of-the-art performance, surpassing existing methods such as GPS, Adapter Tuning, and LoRA.
  arXiv  Detail & Related papers  (2025-06-14T14:41:03Z)
• SLED: A Speculative LLM Decoding Framework for Efficient Edge Serving [7.69991252191073]
  acronym is a framework that allows lightweight edge devices to draft multiple candidate tokens locally using diverse draft models.<n>A single, shared edge server verifies the tokens utilizing a more precise target model.<n>Our initial experiments with Jetson Orin Nano, Raspberry Pi 4B/5, and an edge server equipped with 4 Nvidia A100 GPUs indicate substantial benefits.
  arXiv  Detail & Related papers  (2025-06-11T04:55:54Z)
• Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition [95.54406667705999]
  Pangu Embedded is an efficient Large Language Model (LLM) reasoner developed on Ascend Neural Processing Units (NPUs)<n>It addresses the significant computational costs and inference latency challenges prevalent in existing reasoning-optimized LLMs.<n>It delivers rapid responses and state-of-the-art reasoning quality within a single, unified model architecture.
  arXiv  Detail & Related papers  (2025-05-28T14:03:02Z)
• A Sensitivity-Driven Expert Allocation Method in LoRA-MoE for Efficient Fine-Tuning [0.6906005491572401]
  We propose a method for allocating expert numbers based on parameter sensitivity LoRA-SMoE.<n> Experimental results demonstrate that our LoRA-SMoE approach can enhance model performance while reducing the number of trainable parameters.
  arXiv  Detail & Related papers  (2025-05-06T13:22:46Z)
• EfficientLLM: Scalable Pruning-Aware Pretraining for Architecture-Agnostic Edge Language Models [25.058673320372677]
  Large language models (LLMs) driven by scaling laws, achieve intelligence emergency in large model sizes.<n>This work proposes the pruning-aware pretraining, focusing on retaining performance of much larger optimized models.<n>We reveal that it achieves top-quality edge language models, termed EfficientLLM, by scaling up LLM compression and extending its boundary.
  arXiv  Detail & Related papers  (2025-02-10T16:51:03Z)
• IterIS: Iterative Inference-Solving Alignment for LoRA Merging [14.263218227928729]
  Low-rank adaptations (LoRAs) are widely used to fine-tune large models across various domains for specific downstream tasks. LoRA merging presents an effective solution by combining multiple LoRAs into a unified adapter while maintaining data privacy.
  arXiv  Detail & Related papers  (2024-11-21T19:04:02Z)
• Pluto and Charon: A Time and Memory Efficient Collaborative Edge AI Framework for Personal LLMs Fine-Tuning [13.26886445965894]
  Pluto and Charon (PAC) is a time and memory efficient collaborative edge AI framework for personal LLMs fine-tuning. PAC implements a personal LLMs fine-tuning technique that is efficient in terms of parameters, time, and memory. Extensive evaluation based on prototype implementation demonstrates that PAC remarkably outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-08-20T11:30:12Z)
• SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning [63.93193829913252]
  We propose an innovative METL strategy called SHERL for resource-limited scenarios. In the early route, intermediate outputs are consolidated via an anti-redundancy operation. In the late route, utilizing minimal late pre-trained layers could alleviate the peak demand on memory overhead.
  arXiv  Detail & Related papers  (2024-07-10T10:22:35Z)
• EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Layerwise Unified Compression and Adaptive Layer Tuning and Voting [12.006890185810322]
  We introduce a computation- and memory-efficient LLM tuning framework, called Edge-LLM, to facilitate affordable and effective LLM adaptation on edge devices. Specifically, Edge-LLM features three core components: (1) a layer-wise unified compression (LUC) technique to reduce the computation overhead by generating layer-wise pruning sparsity and quantization bit-width policies, (2) an adaptive layer tuning and voting scheme to reduce the memory overhead by reducing the backpropagation depth, and (3) a complementary hardware scheduling strategy to handle the irregular computation patterns introduced by LUC and adaptive layer tuning.
  arXiv  Detail & Related papers  (2024-06-22T06:51:47Z)
• Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient [57.9629676017527]
  We propose an optimization-based structural pruning on Large-Language Models. We learn the pruning masks in a probabilistic space directly by optimizing the loss of the pruned model. Our method operates for 2.7 hours with around 35GB memory for the 13B models on a single A100 GPU.
  arXiv  Detail & Related papers  (2024-06-15T09:31:03Z)
• VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections [35.133698935322634]
  Large language models (LLMs) have recently emerged as powerful tools for tackling many language-processing tasks. We identify and characterise the important components needed for effective model convergence using gradient descent. This result leads us to a cheap and memory-efficient algorithm for both fine-tuning and pre-training LLMs.
  arXiv  Detail & Related papers  (2024-05-28T09:23:14Z)
• HiRE: High Recall Approximate Top-$k$ Estimation for Efficient LLM Inference [68.59839755875252]
  HiRE comprises of two novel components: (i) a compression scheme to cheaply predict top-$k$ rows/columns with high recall, followed by full computation restricted to the predicted subset, and (ii) DA-TOP-$k$: an efficient multi-device approximate top-$k$ operator. We demonstrate that on a one billion parameter model, HiRE applied to both the softmax as well as feedforward layers, achieves almost matching pretraining and downstream accuracy, and speeds up inference latency by $1.47times$ on a single TPUv5e device.
  arXiv  Detail & Related papers  (2024-02-14T18:04:36Z)
• Time-, Memory- and Parameter-Efficient Visual Adaptation [75.28557015773217]
  We propose an adaptation method which does not backpropagate gradients through the backbone. We achieve this by designing a lightweight network in parallel that operates on features from the frozen, pretrained backbone.
  arXiv  Detail & Related papers  (2024-02-05T10:55:47Z)
• Modality Plug-and-Play: Elastic Modality Adaptation in Multimodal LLMs for Embodied AI [10.82017289243097]
  Large Language Models (LLMs) are capable of reasoning over diverse input data modalities through pre-trained encoders. m-LLM improves the task accuracy by up to 4% compared to the best existing scheme.
  arXiv  Detail & Related papers  (2023-12-13T04:08:59Z)
• Fine-Tuning Language Models with Just Forward Passes [92.04219196752007]
  Fine-tuning language models (LMs) has yielded success on diverse downstream tasks, but as LMs grow in size, backpropagation requires a large amount of memory. We propose a memory-efficient zerothorder (MeZO) to operate in-place, thereby fine-tuning LMs with the same memory footprint as inference.
  arXiv  Detail & Related papers  (2023-05-27T02:28:10Z)
• Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model [89.8764435351222]
  We propose a new family of unbiased estimators called WTA-CRS, for matrix production with reduced variance. Our work provides both theoretical and experimental evidence that, in the context of tuning transformers, our proposed estimators exhibit lower variance compared to existing ones.
  arXiv  Detail & Related papers  (2023-05-24T15:52:08Z)
• Energy-efficient Task Adaptation for NLP Edge Inference Leveraging Heterogeneous Memory Architectures [68.91874045918112]
  adapter-ALBERT is an efficient model optimization for maximal data reuse across different tasks. We demonstrate the advantage of mapping the model to a heterogeneous on-chip memory architecture by performing simulations on a validated NLP edge accelerator.
  arXiv  Detail & Related papers  (2023-03-25T14:40:59Z)
• A Privacy-Preserving-Oriented DNN Pruning and Mobile Acceleration Framework [56.57225686288006]
  Weight pruning of deep neural networks (DNNs) has been proposed to satisfy the limited storage and computing capability of mobile edge devices. Previous pruning methods mainly focus on reducing the model size and/or improving performance without considering the privacy of user data. We propose a privacy-preserving-oriented pruning and mobile acceleration framework that does not require the private training dataset.
  arXiv  Detail & Related papers  (2020-03-13T23:52:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.