Cover Image

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lu, Yao, Luan, Zhongzhi, Li, Gen, Qi, Jiaxing, Ma, Shiqing, Han, Bin, Shang, Shizhe, Yang, Hailong, Qian, Depei
Format:	Preprint
Published:	2026
Subjects:	Distributed, Parallel, and Cluster Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

FDLoRA: Personalized Federated Learning of Large Language Model via Dual LoRA Tuning
by: QI, Jiaxing, et al.
Published: (2024)

INSPIRIT: Optimizing Heterogeneous Task Scheduling through Adaptive Priority in Task-based Runtime Systems
by: Wang, Yiqing, et al.
Published: (2024)

Minions: Accelerating Large Language Model Inference with Aggregated Speculative Execution
by: Wang, Siqi, et al.
Published: (2024)

PRAGMA: A Profiling-Reasoned Multi-Agent Framework for Automatic Kernel Optimization
by: Lei, Kelun, et al.
Published: (2025)

Scaling All-to-all Operations Across Emerging Many-Core Supercomputers
by: Kinkead, Shannon, et al.
Published: (2026)

LOw-cOst yet High-Performant Sparse Matrix-Matrix Multiplication on Arm SME Architectures
by: Lei, Kelun, et al.
Published: (2025)

Bandwidth-Aware and Cost-Efficient Pipeline Parallel Scheduling in Geo-Distributed LLM Training
by: Zhang, Han, et al.
Published: (2026)

Otus Supercomputer
by: Ehtesabi, Sadaf, et al.
Published: (2025)

DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference
by: Wu, Yongtong, et al.
Published: (2026)

ArcLight: A Lightweight LLM Inference Architecture for Many-Core CPUs
by: Xu, Yuzhuang, et al.
Published: (2026)

MoA-Off: Adaptive Heterogeneous Modality-Aware Offloading with Edge-Cloud Collaboration for Efficient Multimodal LLM Inference
by: Yang, Zheming, et al.
Published: (2025)

SPIN: Accelerating Large Language Model Inference with Heterogeneous Speculative Models
by: Chen, Fahao, et al.
Published: (2025)

Federated Inference for Heterogeneous LLM Communication and Collaboration
by: Chen, Zihan, et al.
Published: (2026)

KIS-S: A GPU-Aware Kubernetes Inference Simulator with RL-Based Auto-Scaling
by: Zhang, Guilin, et al.
Published: (2025)

Bandwidth-Aware Network Topology Optimization for Decentralized Learning
by: Shen, Yipeng, et al.
Published: (2025)

Enabling Message Passing Interface Containers on the LUMI Supercomputer
by: Lazzaro, Alfio
Published: (2024)

Analysis of the Performance of the Matrix Multiplication Algorithm on the Cirrus Supercomputer
by: Adefemi, Temitayo
Published: (2024)

Arrow: Adaptive Scheduling Mechanisms for Disaggregated LLM Inference Architecture
by: Wu, Yu, et al.
Published: (2025)

Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs
by: Jiang, Youhe, et al.
Published: (2025)

CB-SpMV:A Data Aggregating and Balance Algorithm for Cache-Friendly Block-Based SpMV on GPUs
by: Cong, Xing, et al.
Published: (2026)

FATE: Future-State-Aware Scheduling for Heterogeneous LLM Workflows
by: Huang, Zirui, et al.
Published: (2026)

Argus: Token Aware Distributed LLM Inference Optimization
by: Wu, Panlong, et al.
Published: (2025)

Toward Sustainability-Aware LLM Inference on Edge Clusters
by: Rajashekar, Kolichala, et al.
Published: (2025)

Leveraging Hardware Performance Counters for Predicting Workload Interference in Vector Supercomputers
by: Shubham, et al.
Published: (2024)

TX-Digital Twin: Visualizing Supercomputer GPU Performance Data Stream
by: Baskakova, Elena, et al.
Published: (2026)

MalleTrain: Deep Neural Network Training on Unfillable Supercomputer Nodes
by: Ma, Xiaolong, et al.
Published: (2024)

LLM-CoOpt: A Co-Design and Optimization Framework for Efficient LLM Inference on Heterogeneous Platforms
by: Kong, Jie, et al.
Published: (2026)

Offline Energy-Optimal LLM Serving: Workload-Based Energy Models for LLM Inference on Heterogeneous Systems
by: Wilkins, Grant, et al.
Published: (2024)

MSAO: Adaptive Modality Sparsity-Aware Offloading with Edge-Cloud Collaboration for Efficient Multimodal LLM Inference
by: Yang, Zheming, et al.
Published: (2026)

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

Supercomputer 3D Digital Twin for User Focused Real-Time Monitoring
by: Bergeron, William, et al.
Published: (2024)

Ghidorah: Fast LLM Inference on Edge with Speculative Decoding and Hetero-Core Parallelism
by: Wei, Jinhui, et al.
Published: (2025)

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

Taming Request Imbalance: SLO-Aware Scheduling for Disaggregated LLM Inference
by: Wang, Qipeng
Published: (2026)

GoodServe: Towards High-Goodput Serving of Agentic LLM Inferences over Heterogeneous Resources
by: Du, Boxiao, et al.
Published: (2026)

Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference
by: Li, Rongzhi, et al.
Published: (2025)

Aging-aware CPU Core Management for Embodied Carbon Amortization in Cloud LLM Inference
by: Hewage, Tharindu B., et al.
Published: (2025)

HexGen: Generative Inference of Large Language Model over Heterogeneous Environment
by: Jiang, Youhe, et al.
Published: (2023)

HexAGenT: Efficient Agentic LLM Serving via Workflow- and Heterogeneity-Aware Scheduling
by: Peng, You, et al.
Published: (2026)

Frenzy: A Memory-Aware Serverless LLM Training System for Heterogeneous GPU Clusters
by: Chang, Zihan, et al.
Published: (2024)