Imagen de Portada

QPART: Adaptive Model Quantization and Dynamic Workload Balancing for Accuracy-aware Edge Inference

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Xiangchen, Ghafouri, Saeid, Ji, Bo, Vandierendonck, Hans, John, Deepu, Nikolopoulos, Dimitrios S.
Formato:	Preprint
Publicado:	2025
Materias:	Distributed, Parallel, and Cluster Computing Artificial Intelligence Machine Learning Performance
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

FACT: Compositional Kernel Synthesis with a Three-Stage Agentic Workflow
por: Heidari, Sina, et al.
Publicado: (2026)

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

SLED: A Speculative LLM Decoding Framework for Efficient Edge Serving
por: Li, Xiangchen, et al.
Publicado: (2025)

IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency
por: Ghafouri, Saeid, et al.
Publicado: (2023)

APEX: Asynchronous Parallel CPU-GPU Execution for Online LLM Inference on Constrained GPUs
por: Fan, Jiakun, et al.
Publicado: (2025)

WISP: Waste- and Interference-Suppressed Distributed Speculative LLM Serving at the Edge via Dynamic Drafting and SLO-Aware Batching
por: Li, Xiangchen, et al.
Publicado: (2026)

ConfigSpec: Profiling-Based Configuration Selection for Distributed Edge--Cloud Speculative LLM Serving
por: Li, Xiangchen, et al.
Publicado: (2026)

Collaborative Processing for Multi-Tenant Inference on Memory-Constrained Edge TPUs
por: Ng, Nathan, et al.
Publicado: (2026)

Minos: Systematically Classifying Performance and Power Characteristics of GPU Workloads on HPC Clusters
por: Jain, Rutwik, et al.
Publicado: (2026)

Profiling Concurrent Vision Inference Workloads on NVIDIA Jetson -- Extended
por: Chakraborty, Abhinaba, et al.
Publicado: (2025)

Opt4GPTQ: Co-Optimizing Memory and Computation for 4-bit GPTQ Quantized LLM Inference on Heterogeneous Platforms
por: Zhang, Yaozheng, et al.
Publicado: (2025)

xMem: A CPU-Based Approach for Accurate Estimation of GPU Memory in Deep Learning Training Workloads
por: Shi, Jiabo, et al.
Publicado: (2025)

BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving Systems
por: Wang, Yuxin, et al.
Publicado: (2024)

Active Inference-Based Adaptive Routing for Heterogeneous Edge AI Services
por: Wang, Zihang, et al.
Publicado: (2026)

On Optimizing Locality of Graph Transposition on Modern Architectures
por: Esfahani, Mohsen Koohi, et al.
Publicado: (2025)

Taming the Memory Footprint Crisis: System Design for Production Diffusion LLM Serving
por: Fan, Jiakun, et al.
Publicado: (2025)

TOD: Transprecise Object Detection to Maximise Real-Time Accuracy on the Edge
por: Lee, JunKyu, et al.
Publicado: (2021)

Bridding OT and PaaS in Edge-to-Cloud Continuum
por: Barrios, Carlos J, et al.
Publicado: (2025)

Communication-Aware Diffusion Load Balancing for Persistently Interacting Objects
por: Taylor, Maya, et al.
Publicado: (2026)

Reducing Tail Latencies Through Environment- and Neighbour-aware Thread Management
por: Jeffery, Andrew, et al.
Publicado: (2024)

WebAssembly and Unikernels: A Comparative Study for Serverless at the Edge
por: Besozzi, Valerio, et al.
Publicado: (2025)

Less is More: Optimizing Function Calling for LLM Execution on Edge Devices
por: Paramanayakam, Varatheepan, et al.
Publicado: (2024)

Ecomap: Sustainability-Driven Optimization of Multi-Tenant DNN Execution on Edge Servers
por: Paramanayakam, Varatheepan, et al.
Publicado: (2025)

Characterizing and Optimizing LLM Inference Workloads on CPU-GPU Coupled Architectures
por: Vellaisamy, Prabhu, et al.
Publicado: (2025)

ADELIA: Automatic Differentiation for Efficient Laplace Inference Approximations
por: Boudaoud, Afif, et al.
Publicado: (2026)

LMDeploy Accelerates Mixed-Precision LLM Inference with TurboMind
por: Zhang, Li, et al.
Publicado: (2025)

Multi-DNN Inference of Sparse Models on Edge SoCs
por: Luo, Jiawei, et al.
Publicado: (2026)

Sponge: Inference Serving with Dynamic SLOs Using In-Place Vertical Scaling
por: Razavi, Kamran, et al.
Publicado: (2024)

Fine-Grained Energy Prediction For Parallellized LLM Inference With PIE-P
por: Dutt, Anurag, et al.
Publicado: (2025)

Understanding Inference Scaling for LLMs: Bottlenecks, Trade-offs, and Performance Principles
por: Arif, Moiz, et al.
Publicado: (2026)

The Energy Cost of Execution-Idle in GPU Clusters
por: Lei, Yiran, et al.
Publicado: (2026)

CoFormer: Collaborating with Heterogeneous Edge Devices for Scalable Transformer Inference
por: Xu, Guanyu, et al.
Publicado: (2025)

Energy-Optimized Scheduling for AIoT Workloads Using TOPSIS
por: Pradeep, Preethika, et al.
Publicado: (2025)

RAPID-LLM: Resilience-Aware Performance analysis of Infrastructure for Distributed LLM Training and Inference
por: Karfakis, George, et al.
Publicado: (2025)

HybridGen: Efficient LLM Generative Inference via CPU-GPU Hybrid Computing
por: Lin, Mao, et al.
Publicado: (2026)

HeteGen: Heterogeneous Parallel Inference for Large Language Models on Resource-Constrained Devices
por: Zhao, Xuanlei, et al.
Publicado: (2024)

Characterizing Adaptive Mesh Refinement on Heterogeneous Platforms with Parthenon-VIBE
por: Poptani, Akash, et al.
Publicado: (2025)

TraDE: Network and Traffic-aware Adaptive Scheduling for Microservices Under Dynamics
por: Chen, Ming, et al.
Publicado: (2024)

CARAT: Client-Side Adaptive RPC and Cache Co-Tuning for Parallel File Systems
por: Rashid, Md Hasanur, et al.
Publicado: (2026)

Modeling and Characterizing Service Interference in Dynamic Infrastructures
por: Medel, VÍctor, et al.
Publicado: (2024)