Imagen de Portada

HyperOffload: Graph-Driven Hierarchical Memory Management for Large Language Models on SuperNode Architectures

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Fangxin, Zhang, Qinghua, Shen, Hanjing, Liang, Zhibo, Jiang, Li, Guan, Haibing, Bao, Chong, Jin, Xuefeng
Formato:	Preprint
Publicado:	2026
Materias:	Distributed, Parallel, and Cluster Computing Artificial Intelligence Hardware Architecture
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Efficient Architecture for RISC-V Vector Memory Access
por: Guan, Hongyi, et al.
Publicado: (2025)

PIUMA: Programmable Integrated Unified Memory Architecture
por: Aananthakrishnan, Sriram, et al.
Publicado: (2020)

Enabling Time-Aware Priority Traffic Management over Distributed FPGA Nodes
por: Scionti, Alberto, et al.
Publicado: (2025)

Optimizing Offload Performance in Heterogeneous MPSoCs
por: Colagrande, Luca, et al.
Publicado: (2024)

Understanding Bottlenecks for Efficiently Serving LLM Inference With KV Offloading
por: Meng, William, et al.
Publicado: (2025)

New Tools, Programming Models, and System Support for Processing-in-Memory Architectures
por: Oliveira, Geraldo F.
Publicado: (2025)

Knowledge-Guided Attention-Inspired Learning for Task Offloading in Vehicle Edge Computing
por: Ma, Ke, et al.
Publicado: (2025)

DMA-Latte: Expanding the Reach of DMA Offloads to Latency-bound ML Communication
por: Pati, Suchita, et al.
Publicado: (2025)

Generic and ML Workloads in an HPC Datacenter: Node Energy, Job Failures, and Node-Job Analysis
por: Chu, Xiaoyu, et al.
Publicado: (2024)

Microbenchmark-Driven Analytical Performance Modeling Across Modern GPU Architectures
por: Jarmusch, Aaron, et al.
Publicado: (2026)

Taming Offload Overheads in a Massively Parallel Open-Source RISC-V MPSoC: Analysis and Optimization
por: Colagrande, Luca, et al.
Publicado: (2025)

FpgaHub: Fpga-centric Hyper-heterogeneous Computing Platform for Big Data Analytics
por: Wang, Zeke, et al.
Publicado: (2025)

Fine-Grained Power and Energy Attribution on AMD GPU/APU-Based Exascale Nodes
por: McDaniel, Adam, et al.
Publicado: (2026)

Memory-Centric Computing: Solving Computing's Memory Problem
por: Mutlu, Onur, et al.
Publicado: (2025)

Analyzing a Two-Tier Disaggregated Memory Protection Scheme Based on Memory Replication
por: Volos, Haris, et al.
Publicado: (2025)

RailX: A Flexible, Scalable, and Low-Cost Network Architecture for Hyper-Scale LLM Training Systems
por: Feng, Yinxiao, et al.
Publicado: (2025)

General-Purpose Multicore Architectures
por: Ghose, Saugata
Publicado: (2024)

Dynamic Simultaneous Multithreaded Architecture
por: Ortiz-Arroyo, Daniel, et al.
Publicado: (2024)

A Modern Primer on Processing in Memory
por: Mutlu, Onur, et al.
Publicado: (2020)

HieraSparse: Hierarchical Semi-Structured Sparse KV Attention
por: Wang, Haoxuan, et al.
Publicado: (2026)

SpArch: Efficient Architecture for Sparse Matrix Multiplication
por: Zhang, Zhekai, et al.
Publicado: (2020)

Accelerating Triangle Counting with Real Processing-in-Memory Systems
por: Asquini, Lorenzo, et al.
Publicado: (2025)

Balanced Data Placement for GEMV Acceleration with Processing-In-Memory
por: Ibrahim, Mohamed Assem, et al.
Publicado: (2024)

Memory-Centric Computing: Recent Advances in Processing-in-DRAM
por: Mutlu, Onur, et al.
Publicado: (2024)

cMPI: Using CXL Memory Sharing for MPI One-Sided and Two-Sided Inter-Node Communications
por: Wang, Xi, et al.
Publicado: (2025)

HARP: A Taxonomy for Heterogeneous and Hierarchical Processors for Mixed-reuse Workloads
por: Garg, Raveesh, et al.
Publicado: (2025)

Navigating the Landscape of Distributed File Systems: Architectures, Implementations, and Considerations
por: Pan, Xueting, et al.
Publicado: (2024)

FengHuang: Next-Generation Memory Orchestration for AI Inferencing
por: Li, Jiamin, et al.
Publicado: (2025)

Handling of Memory Page Faults during Virtual-Address RDMA
por: Psistakis, Antonis
Publicado: (2025)

DCRA: A Distributed Chiplet-based Reconfigurable Architecture for Irregular Applications
por: Orenes-Vera, Marcelo, et al.
Publicado: (2023)

iHAC: A Hybrid Cluster Architecture for Enhanced Performance and Resilience
por: Muntaka, Siddique Abubakr, et al.
Publicado: (2026)

A Heterogeneous Chiplet Architecture for Accelerating End-to-End Transformer Models
por: Sharma, Harsh, et al.
Publicado: (2023)

Pooling Engram Conditional Memory in Large Language Models using CXL
por: Ma, Ruiyang, et al.
Publicado: (2026)

TeraPool: A Physical Design Aware, 1024 RISC-V Cores Shared-L1-Memory Scaled-up Cluster Design with High Bandwidth Main Memory Link
por: Zhang, Yichao, et al.
Publicado: (2026)

How Fast Can Graph Computations Go on Fine-grained Parallel Architectures
por: Wang, Yuqing, et al.
Publicado: (2025)

BlockAMC: Scalable In-Memory Analog Matrix Computing for Solving Linear Systems
por: Pan, Lunshuai, et al.
Publicado: (2024)

Survey of Disaggregated Memory: Cross-layer Technique Insights for Next-Generation Datacenters
por: Wang, Jing, et al.
Publicado: (2025)

UniFormer: Unified and Efficient Transformer for Reasoning Across General and Custom Computing
por: Ran, Zhuoheng, et al.
Publicado: (2025)

Exploring the Efficiency of 3D-Stacked AI Chip Architecture for LLM Inference with Voxel
por: Liu, Yiqi, et al.
Publicado: (2026)

PAM: Processing Across Memory Hierarchy for Efficient KV-centric LLM Serving System
por: Liu, Lian, et al.
Publicado: (2026)