Copertina

Scaling Up On-Device LLMs via Active-Weight Swapping Between DRAM and Flash

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Jia, Fucheng, Wu, Zewen, Jiang, Shiqi, Jiang, Huiqiang, Zhang, Qianxi, Yang, Yuqing, Liu, Yunxin, Ren, Ju, Zhang, Deyu, Cao, Ting
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Empowering In-Browser Deep Learning Inference on Edge Devices with Just-in-Time Kernel Optimizations
di: Jia, Fucheng, et al.
Pubblicazione: (2023)

Scaling LLM Test-Time Compute with Mobile NPU on Smartphones
di: Hao, Zixu, et al.
Pubblicazione: (2025)

AdaNav: Adaptive Reasoning with Uncertainty for Vision-Language Navigation
di: Ding, Xin, et al.
Pubblicazione: (2025)

Em-Garde: A Propose-Match Framework for Proactive Streaming Video Understanding
di: Zheng, Yikai, et al.
Pubblicazione: (2026)

Making Every Frame Matter: Continuous Activity Recognition in Streaming Video via Adaptive Video Context Modeling
di: Wu, Hao, et al.
Pubblicazione: (2024)

KVNAND: Efficient On-Device Large Language Model Inference Using DRAM-Free In-Flash Computing
di: Deng, Lishuo, et al.
Pubblicazione: (2025)

A First Look At Efficient And Secure On-Device LLM Inference Against KV Leakage
di: Yang, Huan, et al.
Pubblicazione: (2024)

MemCompiler: Compile, Don't Inject -- State-Conditioned Memory for Embodied Agents
di: Ding, Xin, et al.
Pubblicazione: (2026)

Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management
di: Li, Mo, et al.
Pubblicazione: (2025)

EmbodiSkill: Skill-Aware Reflection for Self-Evolving Embodied Agents
di: Ju, Ruofei, et al.
Pubblicazione: (2026)

Accelerating Prefilling via Decoding-time Contribution Sparsity
di: He, Zhiyuan, et al.
Pubblicazione: (2025)

MTraining: Distributed Dynamic Sparse Attention for Efficient Ultra-Long Context Training
di: Li, Wenxuan, et al.
Pubblicazione: (2025)

MobiFuse: A High-Precision On-device Depth Perception System with Multi-Data Fusion
di: Zhang, Jinrui, et al.
Pubblicazione: (2024)

SwapNet: Efficient Swapping for DNN Inference on Edge AI Devices Beyond the Memory Budget
di: Wang, Kun, et al.
Pubblicazione: (2024)

LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression
di: Jiang, Huiqiang, et al.
Pubblicazione: (2023)

Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts
di: Li, Yunxin, et al.
Pubblicazione: (2024)

SortedRL: Accelerating RL Training for LLMs through Online Length-Aware Scheduling
di: Zhang, Yiqi, et al.
Pubblicazione: (2026)

FP-Rowhammer: DRAM-Based Device Fingerprinting
di: Venugopalan, Hari, et al.
Pubblicazione: (2023)

JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency
di: Cai, Aichen, et al.
Pubblicazione: (2026)

LeanK: Learnable K Cache Channel Pruning for Efficient Decoding
di: Zhang, Yike, et al.
Pubblicazione: (2025)

Revisiting DRAM Read Disturbance: Identifying Inconsistencies Between Experimental Characterization and Device-Level Studies
di: Luo, Haocong, et al.
Pubblicazione: (2025)

Settling Weighted Token Swapping up to Algorithmic Barriers
di: Wein, Nicole, et al.
Pubblicazione: (2025)

Weisfeiler‐Lehman Kernel Augmented Product Representation for Queries on Large‐Scale BIM Scenes
di: Huiqiang Hu, et al.
Pubblicazione: (2025)

FlashRecovery: Fast and Low-Cost Recovery from Failures for Large-Scale Training of LLMs
di: Zhang, Haijun, et al.
Pubblicazione: (2025)

Distinguishing Translations by Human, NMT, and ChatGPT: A Linguistic and Statistical Approach
di: Jiang, Zhaokun, et al.
Pubblicazione: (2023)

Convergences and Divergences between Automatic Assessment and Human Evaluation: Insights from Comparing ChatGPT-Generated Translation and Neural Machine Translation
di: Jiang, Zhaokun, et al.
Pubblicazione: (2024)

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
di: Liu, Di, et al.
Pubblicazione: (2024)

Hardware Co-Design Scaling Laws via Roofline Modelling for On-Device LLMs
di: Sun, Luoyang, et al.
Pubblicazione: (2026)

Uncovering the Role of Initial Saliency in U-Shaped Attention Bias: Scaling Initial Token Weight for Enhanced Long-Text Processing
di: Qiang, Zewen, et al.
Pubblicazione: (2025)

Position Engineering: Boosting Large Language Models through Positional Information Manipulation
di: He, Zhiyuan, et al.
Pubblicazione: (2024)

An Analytic Model to Determine the Interstitial-Solute Energetics and Underlying Mechanism in Refractory High-Entropy Alloys
di: Zhu, Qianxi, et al.
Pubblicazione: (2025)

Vec-LUT: Vector Table Lookup for Parallel Ultra-Low-Bit LLM Inference on Edge Devices
di: Li, Xiangyu, et al.
Pubblicazione: (2025)

Zoomer: Adaptive Image Focus Optimization for Black-box MLLM
di: Qian, Jiaxu, et al.
Pubblicazione: (2025)

ProRe: A Proactive Reward System for GUI Agents via Reasoner-Actor Collaboration
di: Dai, Gaole, et al.
Pubblicazione: (2025)

Advancing Mobile GUI Agents: A Verifier-Driven Approach to Practical Deployment
di: Dai, Gaole, et al.
Pubblicazione: (2025)

AVA: Towards Agentic Video Analytics with Vision Language Models
di: Yan, Yuxuan, et al.
Pubblicazione: (2025)

PUDTune: Multi-Level Charging for High-Precision Calibration in Processing-Using-DRAM
di: Kubo, Tatsuya, et al.
Pubblicazione: (2025)

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression
di: Li, Yucheng, et al.
Pubblicazione: (2025)

Mitigate Position Bias in Large Language Models via Scaling a Single Dimension
di: Yu, Yijiong, et al.
Pubblicazione: (2024)

LLMs Meet Long Video: Advancing Long Video Question Answering with An Interactive Visual Adapter in LLMs
di: Li, Yunxin, et al.
Pubblicazione: (2024)