Imagen de Portada

Accuracy-Delay Trade-Off in LLM Offloading via Token-Level Uncertainty

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kim, Yumin, Lyu, Hyeonsu, Lee, Minjae, Yang, Hyun Jong
Formato:	Preprint
Publicado:	2026
Materias:	Systems and Control Artificial Intelligence Distributed, Parallel, and Cluster Computing
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

On-demand Cold Start Frequency Reduction with Off-Policy Reinforcement Learning in Serverless Computing
por: Agarwal, Siddharth, et al.
Publicado: (2023)

A Case Study of API Design for Interoperability and Security of the Internet of Things
por: Kim, Dongha, et al.
Publicado: (2024)

AdapTBF: Decentralized Bandwidth Control via Adaptive Token Borrowing for HPC Storage
por: Rashid, Md Hasanur, et al.
Publicado: (2026)

SPARe: Stacked Parallelism with Adaptive Reordering for Fault-Tolerant LLM Pretraining Systems with 100k+ GPUs
por: Lee, Jin, et al.
Publicado: (2026)

Efficient Coordination for Distributed Discrete-Event Systems
por: Jun, Byeonggil, et al.
Publicado: (2024)

Taming Latency-Memory Trade-Off in MoE-Based LLM Serving via Fine-Grained Expert Offloading
por: Yu, Hanfei, et al.
Publicado: (2025)

Intelligent Router for LLM Workloads: Improving Performance Through Workload-Aware Load Balancing
por: Jain, Kunal, et al.
Publicado: (2024)

Pythia: Exploiting Workflow Predictability for Efficient Agent-Native LLM Serving
por: Yu, Shan, et al.
Publicado: (2026)

From Barrier to Bridge: The Case for AI Data Center/Power Grid Co-Design
por: Bashir, Noman, et al.
Publicado: (2026)

Multi-Agentic AI for Fairness-Aware and Accelerated Multi-modal Large Model Inference in Real-world Mobile Edge Networks
por: Li, Haiyuan, et al.
Publicado: (2026)

Systemic approach for modeling a generic smart grid
por: Amor, Sofiane Ben, et al.
Publicado: (2025)

A Deep Recurrent-Reinforcement Learning Method for Intelligent AutoScaling of Serverless Functions
por: Agarwal, Siddharth, et al.
Publicado: (2023)

Input-Based Ensemble-Learning Method for Dynamic Memory Configuration of Serverless Computing Functions
por: Agarwal, Siddharth, et al.
Publicado: (2024)

Tackling the Crowdsourced Shared-Trip Delivery Problem at Scale with a Novel Decomposition Heuristic
por: Yang, Dingtong, et al.
Publicado: (2022)

PMU-based Distributed Non-iterative Algorithm for Real-time Voltage Stability Monitoring
por: Guddanti, Kishan Prudhvi, et al.
Publicado: (2019)

Hybrid Cooperative Co-Evolution Algorithm for Deadlock-prone Distributed Assembly Flowshop Scheduling with Limited buffers Using Petri nets
por: Wang, Siyi, et al.
Publicado: (2024)

Plug & Offload: Transparently Offloading TCP Stack onto Off-path SmartNIC with PnO-TCP
por: Nan, Hailong, et al.
Publicado: (2025)

Adaptive Workload Distribution for Accuracy-aware DNN Inference on Collaborative Edge Platforms
por: Taufique, Zain, et al.
Publicado: (2023)

Rethinking Inter-Process Communication with Memory Operation Offloading
por: Park, Misun, et al.
Publicado: (2026)

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference
por: Jeong, Bodon, et al.
Publicado: (2026)

JITServe: SLO-aware LLM Serving with Imprecise Request Information
por: Zhang, Wei, et al.
Publicado: (2025)

AMV-L: Lifecycle-Managed Agent Memory for Tail-Latency Control in Long-Running LLM Systems
por: Bamidele, Emmanuel
Publicado: (2026)

Distributed Difference of Convex Optimization
por: Khatana, Vivek, et al.
Publicado: (2024)

Robust Set Partitioning Strategy for Malicious Information Detection in Large-Scale Internet of Things
por: Suo, Yuhan, et al.
Publicado: (2025)

Designing Dense Satellite Clusters for Distributed Space-based Datacenters
por: Pénot, Jules, et al.
Publicado: (2026)

Load Balancing Using Sparse Communication
por: Mendelson, Gal, et al.
Publicado: (2022)

Vessim: A Testbed for Carbon-Aware Applications and Systems
por: Wiesner, Philipp, et al.
Publicado: (2023)

Iterative Thresholding and Projection Algorithms and Model-Based Deep Neural Networks for Sparse LQR Control Design
por: Cho, Myung
Publicado: (2022)

Deployment of Containerized Simulations in an API-Driven Distributed Infrastructure
por: Kraus, Tim, et al.
Publicado: (2025)

Distribution and Management of Datacenter Load Decoupling
por: Lin, Liuzixuan, et al.
Publicado: (2025)

Stannic: Systolic STochAstic ONliNe SchedulIng AcCelerator
por: Ross, Adam H., et al.
Publicado: (2025)

Thinking fast and slow -- a cognitive inspired framework for decision intelligence for power systems
por: Mathur, Apoorv
Publicado: (2026)

H-MBR: Hypervisor-level Memory Bandwidth Reservation for Mixed Criticality Systems
por: Oliveira, Afonso, et al.
Publicado: (2025)

MQFQ-Sticky: Fair Queueing For Serverless GPU Functions
por: Fuerst, Alexander, et al.
Publicado: (2025)

GPUArmor: A Hardware-Software Co-design for Efficient and Scalable Memory Safety on GPUs
por: Ziad, Mohamed Tarek Ibn, et al.
Publicado: (2025)

TALICS$^3$: Tape Library Cloud Storage System Simulator
por: Arslan, Suayb S., et al.
Publicado: (2024)

Finite State Machines-Based Path-Following Collaborative Computing Strategy for Emergency UAV Swarms
por: Hu, Jialin, et al.
Publicado: (2024)

Carbon-Aware Quality Adaptation for Energy-Intensive Services
por: Wiesner, Philipp, et al.
Publicado: (2024)

Computationally Efficient Laplacian CL-colME
por: Stankovic, Nikola
Publicado: (2026)

AI-focused HPC Data Centers Can Provide More Power Grid Flexibility and at Lower Cost
por: Zhou, Yihong, et al.
Publicado: (2024)