arXiv subjects

Liujianfu Wang

Publications and source records attributed to Liujianfu Wang.

5 recordsLinked to original sources

arXiv2026

Broadcast Rate Limits in Wi-Fi: A Forgotten Bottleneck for Collaborative Edge LLM Inference

LLM deployment is migrating from data centers to edge devices, where Mixture-of-Experts (MoE) models offer a promising path: sparse expert activation allows the model to be spread across multiple low-cost edge nodes. Distributed MoE inference repeatedly dispatches embeddings from one main node to many workers - a one-to-many pattern poorly served by the sequential unicasts of mainstream stacks (NCCL, TCP), yet naturally matched by UDP broadcast. We propose a UDP broadcast method for collaborative edge MoE inference, augmented with timeout-driven retransmission exploiting near deterministic latency in distributed MoE for reliability and unordered result gathering for robustness to expert mispredictions, yielding a consistent 1.4x speedup over NCCL and TCP on a wired 8-node cluster. In wireless settings, however, we uncover a deeper, long-forgotten bottleneck: IEEE 802.11 caps broadcast rates at 54 Mbps regardless of physical-layer capacity - a legacy policy built for sparse control traffic, not edge AI. NS-3 simulations at distances 1m, 2m and 5m show that the optimal rates are much higher (64x, 43x, and 32x, respectively) than the 54 Mbps cap applied in standard. Thus, we argue that broadcast is no longer a control-plane relic: it is time for Wi-Fi standards to treat it as a high-throughput data-plane citizen.

cs.NI↗

arXiv2026

LLMind 2.0: Distributed IoT Automation with Natural Language M2M Communication and Lightweight LLM Agents

Recent advances in large language models (LLMs) have generated great interest in their applications for IoT automation and device management. However, centralized approaches struggle to scale across heterogeneous, large-scale systems. We present LLMind 2.0, a distributed framework that embeds lightweight LLM-empowered device agents and adopts natural language for machine-to-machine (M2M) communication. In LLMind 2.0, a central coordinator translates human instructions into natural-language subtask descriptions, which instruct distributed device agents to generate device-specific code locally based on their proprietary APIs. Using natural language as a unified medium overcomes device heterogeneity and enables seamless device collaboration. LLMind 2.0 integrates: 1) a timeout-based deadlock avoidance protocol that coordinates distributed subtask executions, 2) a retrieval-augmented generation (RAG) mechanism for precise subtask-to-API mapping, and 3) fine-tuned lightweight LLMs for reliable, device-specific code generation. Experiments in multi-robot warehouse operations and Wi Fi network deployments show LLMind 2.0 improved scalability, reliability, and responsiveness compared to centralized baselines.

eess.SY↗

arXiv2025

OD-MoE: On-Demand Expert Loading for Cacheless Edge-Distributed MoE Inference

Mixture-of-Experts (MoE), while offering significant advantages as a Large Language Model (LLM) architecture, faces substantial challenges when deployed on low-cost edge devices with tight memory constraints. Expert offloading mitigates this issue by storing expert parameters in CPU memory and caching a subset of popular experts in GPU memory. Although this approach improves GPU memory utilization by caching only the likely-used experts, the GPU memory reserved for expert caching is underutilized compared with dense LLMs. This paper presents OD-MoE, a distributed MoE inference framework that obviates the need for expert caches via fully on-demand expert loading. OD-MoE is built upon two key mechanisms: 1) parallelizing expert loading and expert computation across distributed edge nodes, and 2) an ultra-accurate emulative predictor that forecasts expert activations multiple layers ahead while expert computation is ongoing. With these innovations, OD-MoE dynamically loads each target expert to one of the distributed nodes just-in-time before its activation and promptly evicts it afterward, freeing GPU memory for subsequent experts. We comprehensively benchmark OD-MoE against state-of-the-art MoE offloading systems on a ten-node testbed. Experimental results show that: 1) OD-MoE achieves 99.94% expert activation prediction accuracy, substantially surpassing all existing methods; and 2) OD-MoE delivers approximately 75% of the decoding speed of a fully GPU-cached MoE deployment while using only 1/3 of the GPU memory. More importantly, by eliminating the need for expert caches, OD-MoE enables MoE inference on edge nodes with less-than-1GB GPU memory, paving the way for practical MoE deployment of low-cost IoT devices at the edge in the LLM era.

cs.DC↗

arXiv2025

Cellular-X: An LLM-empowered Cellular Agent for Efficient Base Station Operations

This paper introduces Cellular-X, an LLM-powered agent designed to automate cellular base station (BS) maintenance. Leveraging multimodal LLM and retrieval-augmented generation (RAG) techniques, Cellular-X significantly enhances field engineer efficiency by quickly interpreting user intents, retrieving relevant technical information, and configuring a BS through iterative self-correction. Key features of the demo include automatic customized BS setup, document-based query answering, and voice-controlled configuration reporting and revision. We implemented Cellular-X on a USRP X310 testbed for demonstration. Demo videos and implementation details are available at https://github.com/SeaBreezing/Cellular-X.

cs.NI↗

arXiv2024

Rephrase and Contrast: Fine-Tuning Language Models for Enhanced Understanding of Communication and Computer Networks

Large language models (LLMs) are being widely researched across various disciplines, with significant recent efforts focusing on adapting LLMs for understanding of how communication networks operate. However, over-reliance on prompting techniques hinders the full exploitation of the generalization ability of these models, and the lack of efficient fine-tuning methods prevents the full realization of lightweight LLMs' potential. This paper addresses these challenges by introducing our Rephrase and Contrast (RaC) framework, an efficient fine-tuning framework. RaC enhances LLMs' comprehension and critical thinking abilities by incorporating question reformulation and contrastive analysis of correct and incorrect answers during the fine-tuning process. Experimental results demonstrate a 63.73% accuracy improvement over the foundational model when tested on a comprehensive networking problem set. Moreover, to efficiently construct the dataset for RaC fine-tuning, we develop a GPT-assisted data mining method for generating high-quality question-answer (QA) pairs; furthermore, we introduce ChoiceBoost, a data augmentation technique that expands dataset size while reducing answer-order bias. Apart from these technical innovations, we contribute to the networking community by open-sourcing valuable research resources, including: 1) the fine-tuned networking model referred to as RaC-Net, 2) the training dataset used for fine-tuning the model, 3) three testing problem sets of different difficulties to serve as benchmarks for future research, and 4) code associated with the above resources.

cs.CL↗