Cover Image

ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Luo, Xinhao, Liu, Zihan, Zhou, Yangjie, Fang, Shihan, Huang, Ziyu, Feng, Yu, Zhang, Chen, Sun, Shixuan, Zheng, Zhenzhe, Leng, Jingwen, Guo, Minyi
Format:	Preprint
Published:	2025
Subjects:	Distributed, Parallel, and Cluster Computing Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ClusterFusion++: Expanding Cluster-Level Fusion to Full Transformer-Block Decoding
by: Jin, ChiHeng, et al.
Published: (2026)

FlashFuser: Expanding the Scale of Kernel Fusion for Compute-Intensive Operators via Inter-Core Connection
by: Huang, Ziyu, et al.
Published: (2025)

VQ-LLM: High-performance Code Generation for Vector Quantization Augmented LLM Inference
by: Liu, Zihan, et al.
Published: (2025)

DASH: Deterministic Attention Scheduling for High-throughput Reproducible LLM Training
by: Qiang, Xinwei, et al.
Published: (2026)

eLLM: Elastic Memory Management Framework for Efficient LLM Serving
by: Xu, Jiale, et al.
Published: (2025)

InfiniLoRA: Disaggregated Multi-LoRA Serving for Large Language Models
by: Chen, Hongyu, et al.
Published: (2026)

GPUOS: A GPU Operating System Primitive for Transparent Operation Fusion
by: Yang, Yiwei, et al.
Published: (2026)

GMLake: Efficient and Transparent GPU Memory Defragmentation for Large-scale DNN Training with Virtual Memory Stitching
by: Guo, Cong, et al.
Published: (2024)

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

vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving
by: Xu, Jiale, et al.
Published: (2024)

PRISM: Dynamic Primitive-Based Forecasting for Large-Scale GPU Cluster Workloads
by: Wu, Xin, et al.
Published: (2026)

Towards Resource-Efficient Serverless LLM Inference with SLINFER
by: Xu, Chuhao, et al.
Published: (2025)

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

Vortex: Efficient Sample-Free Dynamic Tensor Program Optimization via Hardware-aware Strategy Space Hierarchization
by: Zhou, Yangjie, et al.
Published: (2024)

Accelerating Sparse DNNs Based on Tiled GEMM
by: Guo, Cong, et al.
Published: (2024)

Predictable LLM Serving on GPU Clusters
by: Darzi, Erfan, et al.
Published: (2025)

Towards Fast Setup and High Throughput of GPU Serverless Computing
by: Zhao, Han, et al.
Published: (2024)

Scaling Up Throughput-oriented LLM Inference Applications on Heterogeneous Opportunistic GPU Clusters with Pervasive Context Management
by: Phung, Thanh Son, et al.
Published: (2025)

gZCCL: Compression-Accelerated Collective Communication Framework for GPU Clusters
by: Huang, Jiajun, et al.
Published: (2023)

Efficiently Executing High-throughput Lightweight LLM Inference Applications on Heterogeneous Opportunistic GPU Clusters with Pervasive Context Management
by: Phung, Thanh Son, et al.
Published: (2025)

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

CALVO: Improve Serving Efficiency for LLM Inferences with Intense Network Demands
by: Wang, Weiye, et al.
Published: (2026)

PecSched: Preemptive and Efficient Cluster Scheduling for LLM Inference
by: Zhang, Zeyu, et al.
Published: (2024)

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

A Taxonomy of Schedulers -- Operating Systems, Clusters and Big Data Frameworks
by: Sliwko, Leszek
Published: (2025)

Zorse: Optimizing LLM Training Efficiency on Heterogeneous GPU Clusters
by: Guo, Runsheng Benson, et al.
Published: (2025)

An Efficient, Reliable and Observable Collective Communication Library in Large-scale GPU Training Clusters
by: Zhang, Mingjun, et al.
Published: (2025)

PlexRL: Cluster-Level Orchestration of Serviceized LLM Execution for RLVR
by: Zhang, Yiqi, et al.
Published: (2026)

Hybrid Heterogeneous Clusters Can Lower the Energy Consumption of LLM Inference Workloads
by: Wilkins, Grant, et al.
Published: (2024)

Beyond A Single AI Cluster: A Survey of Decentralized LLM Training
by: Dong, Haotian, et al.
Published: (2025)

ClusterLess: Deadline-Aware Serverless Workflow Orchestration on Federated Edge Clusters
by: Farahani, Reza, et al.
Published: (2026)

Cronus: Efficient LLM inference on Heterogeneous GPU Clusters via Partially Disaggregated Prefill
by: Liu, Yunzhao, et al.
Published: (2025)

SageSched: Efficient LLM Scheduling Confronting Demand Uncertainty and Hybridity
by: Gan, Zhenghao, et al.
Published: (2026)

Towards Scalable GPU-Accelerated SNN Training via Temporal Fusion
by: Li, Yanchen, et al.
Published: (2024)

A House United Within Itself: SLO-Awareness for On-Premises Containerized ML Inference Clusters via Faro
by: Jeon, Beomyeol, et al.
Published: (2024)

Konflux: Optimized Function Fusion for Serverless Applications
by: Kowallik, Niklas, et al.
Published: (2026)

High-Performance Portable GPU Primitives for Arbitrary Types and Operators in Julia
by: Pilliat, Emmanuel
Published: (2026)

FlexPipe: Adapting Dynamic LLM Serving Through Inflight Pipeline Refactoring in Fragmented Serverless Clusters
by: Lin, Yanying, et al.
Published: (2025)

Composing Distributed Computations Through Task and Kernel Fusion
by: Yadav, Rohan, et al.
Published: (2024)

DynamoLLM: Designing LLM Inference Clusters for Performance and Energy Efficiency
by: Stojkovic, Jovan, et al.
Published: (2024)