Tootfinder

CoFormer: Collaborating with Heterogeneous Edge Devices for Scalable Transformer Inference
Guanyu Xu, Zhiwei Hao, Li Shen, Yong Luo, Fuhui Sun, Xiaoyan Wang, Han Hu, Yonggang Wen
https://arxiv.org/abs/2508.20375

CoFormer: Collaborating with Heterogeneous Edge Devices for Scalable Transformer Inference
The impressive performance of transformer models has sparked the deployment of intelligent applications on resource-constrained edge devices. However, ensuring high-quality service for real-time edge systems is a significant challenge due to the considerable computational demands and resource requirements of these models. Existing strategies typically either offload transformer computations to other devices or directly deploy compressed models on individual edge devices. These strategies, howev…

Task-Oriented Computation Offloading for Edge Inference: An Integrated Bayesian Optimization and Deep Reinforcement Learning Framework
Xian Li, Suzhi Bi, Ying-Jun Angela Zhang
https://arxiv.org/abs/2509.21090

Task-Oriented Computation Offloading for Edge Inference: An Integrated Bayesian Optimization and Deep Reinforcement Learning Framework
Edge intelligence (EI) allows resource-constrained edge devices (EDs) to offload computation-intensive AI tasks (e.g., visual object detection) to edge servers (ESs) for fast execution. However, transmitting high-volume raw task data (e.g., 4K video) over bandwidth-limited wireless networks incurs significant latency. While EDs can reduce transmission latency by degrading data before transmission (e.g., reducing resolution from 4K to 720p or 480p), it often deteriorates inference accuracy, crea…

An RDMA-First Object Storage System with SmartNIC Offload
Yu Zhu, Aditya Dhakal, Pedro Bruel, Gourav Rattihalli, Yunming Xiao, Johann Lombardi, Dejan Milojicic
https://arxiv.org/abs/2509.13997

An RDMA-First Object Storage System with SmartNIC Offload
AI training and inference impose sustained, fine-grain I/O that stresses host-mediated, TCP-based storage paths. Motivated by kernel-bypass networking and user-space storage stacks, we revisit POSIX-compatible object storage for GPU-centric pipelines. We present ROS2, an RDMA-first object storage system design that offloads the DAOS client to an NVIDIA BlueField-3 SmartNIC while leaving the DAOS I/O engine unchanged on the storage server. ROS2 separates a lightweight control plane (gRPC for nam…

Updates to #mastodon complete on my #selfhost.
I think the biggest load on my #footiMac is nginx and my streaming demands. I need to offload that stuff somewhere else.

PricingLogic: Evaluating LLMs Reasoning on Complex Tourism Pricing Tasks
Yunuo Liu, Dawei Zhu, Zena Al-Khalili, Dai Cheng, Yanjun Chen, Dietrich Klakow, Wei Zhang, Xiaoyu Shen
https://arxiv.org/abs/2510.12409

PricingLogic: Evaluating LLMs Reasoning on Complex Tourism Pricing Tasks
We present PricingLogic, the first benchmark that probes whether Large Language Models(LLMs) can reliably automate tourism-related prices when multiple, overlapping fare rules apply. Travel agencies are eager to offload this error-prone task onto AI systems; however, deploying LLMs without verified reliability could result in significant financial losses and erode customer trust. PricingLogic comprises 300 natural-language questions based on booking requests derived from 42 real-world pricing p…

MLP-Offload: Multi-Level, Multi-Path Offloading for LLM Pre-training to Break the GPU Memory Wall
Avinash Maurya, M. Mustafa Rafique, Franck Cappello, Bogdan Nicolae
https://arxiv.org/abs/2509.02480

MLP-Offload: Multi-Level, Multi-Path Offloading for LLM Pre-training to Break the GPU Memory Wall
Training LLMs larger than the aggregated memory of multiple GPUs is increasingly necessary due to the faster growth of LLM sizes compared to GPU memory. To this end, multi-tier host memory or disk offloading techniques are proposed by state of art. Despite advanced asynchronous multi-tier read/write strategies, such offloading strategies result in significant I/O overheads in the critical path of training, resulting in slower iterations. To this end, we propose MLP-Offload, a novel multi-level,…

Towards Confidential and Efficient LLM Inference with Dual Privacy Protection
Honglan Yu, Yibin Wang, Feifei Dai, Dong Liu, Haihui Fan, Xiaoyan Gu
https://arxiv.org/abs/2509.09091

Towards Confidential and Efficient LLM Inference with Dual Privacy Protection
CPU-based trusted execution environments (TEEs) and differential privacy (DP) have gained wide applications for private inference. Due to high inference latency in TEEs, researchers use partition-based approaches that offload linear model components to GPUs. However, dense nonlinear layers of large language models (LLMs) result in significant communication overhead between TEEs and GPUs. DP-based approaches apply random noise to protect data privacy, but this compromises LLM performance and sem…

Bare-Metal RISC-V NVDLA SoC for Efficient Deep Learning Inference
Vineet Kumar (School of Electrical,Electronic Engineering, University College Dublin, Dublin, Ireland, Department of Electronic,Electrical Engineering, Trinity College Dublin, Dublin, Ireland), Ajay Kumar M (School of Electrical,Electronic Engineering, University College Dublin, Dublin, Ireland, Department of Electronic,Electrical Engineering, Trinity College Dublin, Dublin, Ireland), Yike Li (School of Electrical,Elec…

Bare-Metal RISC-V + NVDLA SoC for Efficient Deep Learning Inference
This paper presents a novel System-on-Chip (SoC) architecture for accelerating complex deep learning models for edge computing applications through a combination of hardware and software optimisations. The hardware architecture tightly couples the open-source NVIDIA Deep Learning Accelerator (NVDLA) to a 32-bit, 4-stage pipelined RISC-V core from Codasip called uRISC_V. To offload the model acceleration in software, our toolflow generates bare-metal application code (in assembly), overcoming co…

Autonomous Navigation of Cloud-Controlled Quadcopters in Confined Spaces Using Multi-Modal Perception and LLM-Driven High Semantic Reasoning
Shoaib Ahmmad, Zubayer Ahmed Aditto, Md Mehrab Hossain, Noushin Yeasmin, Shorower Hossain
https://arxiv.org/abs/2508.07885

Autonomous Navigation of Cloud-Controlled Quadcopters in Confined Spaces Using Multi-Modal Perception and LLM-Driven High Semantic Reasoning
This paper introduces an advanced AI-driven perception system for autonomous quadcopter navigation in GPS-denied indoor environments. The proposed framework leverages cloud computing to offload computationally intensive tasks and incorporates a custom-designed printed circuit board (PCB) for efficient sensor data acquisition, enabling robust navigation in confined spaces. The system integrates YOLOv11 for object detection, Depth Anything V2 for monocular depth estimation, a PCB equipped with Ti…

Towards Fundamental Language Models: Does Linguistic Competence Scale with Model Size?
Jaime Collado-Monta\~nez, L. Alfonso Ure\~na-L\'opez, Arturo Montejo-R\'aez
https://arxiv.org/abs/2509.02225

Towards Fundamental Language Models: Does Linguistic Competence Scale with Model Size?
Large Language Models offer impressive language capabilities but suffer from well-known limitations, including hallucinations, biases, privacy concerns, and high computational costs. These issues are largely driven by the combination of linguistic competence and factual memorization within a single monolithic model. This paper introduces and empirically supports the Fundamental Language Model (FLM) paradigm, which advocates for smaller, linguistically competent models that offload factual retri…

An Overlapping Coalition Game Approach for Collaborative Block Mining and Edge Task Offloading in MEC-assisted Blockchain Networks
Licheng Ye, Zehui Xiong, Lin Gao, Dusit Niyato
https://arxiv.org/abs/2508.06031

An Overlapping Coalition Game Approach for Collaborative Block Mining and Edge Task Offloading in MEC-assisted Blockchain Networks
Mobile edge computing (MEC) is a promising technology that enhances the efficiency of mobile blockchain networks, by enabling miners, often acted by mobile users (MUs) with limited computing resources, to offload resource-intensive mining tasks to nearby edge computing servers. Collaborative block mining can further boost mining efficiency by allowing multiple miners to form coalitions, pooling their computing resources and transaction data together to mine new blocks collaboratively. Therefore…

Network-accelerated Active Messages
Md Ashfaqur Rahaman (University of Utah), Alireza Sanaee (University of Cambridge), Todd Thornley (University of Utah), Sebastiano Miano (Politecnico di Milano), Gianni Antichi (Politecnico di Milano,Queen Mary University of London), Brent E. Stephens (Google,University of Utah), Ryan Stutsman (University of Utah)
https://

Network-accelerated Active Messages
Remote Direct Memory Access (RDMA) improves host networking performance by eliminating software and server CPU involvement. However, RDMA has a limited set of operations, is difficult to program, and often requires multiple round trips to perform simple application operations. Programmable SmartNICs provide a different means to offload work from host CPUs to a NIC. This leaves applications with the complex choice of embedding logic as RPC handlers at servers, using RDMA's limited interface to a…

From Patient Burdens to User Agency: Designing for Real-Time Protection Support in Online Health Consultations
Shuning Zhang, Ying Ma, Yongquan `Owen' Hu, Ting Dang, Hong Jia, Xin Yi, Hewu Li
https://arxiv.org/abs/2508.00328

From Patient Burdens to User Agency: Designing for Real-Time Protection Support in Online Health Consultations
Online medical consultation platforms, while convenient, are undermined by significant privacy risks that erode user trust. We first conducted in-depth semi-structured interviews with 12 users to understand their perceptions of security and privacy landscapes on online medical consultation platforms, as well as their practices, challenges and expectation. Our analysis reveals a critical disconnect between users' desires for anonymity and control, and platform realities that offload the responsi…

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[15/15]:
- MLP-Offload: Multi-Level, Multi-Path Offloading for LLM Pre-training to Break the GPU Memory Wall
Avinash Maurya, M. Mustafa Rafique, Franck Cappello, Bogdan Nicolae

SSD Offloading for LLM Mixture-of-Experts Weights Considered Harmful in Energy Efficiency
Kwanhee Kyung, Sungmin Yun, Jung Ho Ahn
https://arxiv.org/abs/2508.06978 https://

SSD Offloading for LLM Mixture-of-Experts Weights Considered Harmful in Energy Efficiency
Large Language Models (LLMs) applying Mixture-of-Experts (MoE) scale to trillions of parameters but require vast memory, motivating a line of research to offload expert weights from fast-but-small DRAM (HBM) to denser Flash SSDs. While SSDs provide cost-effective capacity, their read energy per bit is substantially higher than that of DRAM. This paper quantitatively analyzes the energy implications of offloading MoE expert weights to SSDs during the critical decode stage of LLM inference. Our a…

I think maybe it isn't #mastodon that is slowing down and filling up #footiMac.
It's the 700GB of webcam images/videos.
Just bought a fast dual USB A/C 500GB flash stick to offload this stuff and lighten things up a bit.
This is stuff I need to archive anyway. I want to gradually build a physical USB stick based digital library of webcam imagery from the cams @….
#mastoadmin #weather #webcams