Cover Image

FlashFuser: Expanding the Scale of Kernel Fusion for Compute-Intensive Operators via Inter-Core Connection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Ziyu, Zhou, Yangjie, Liu, Zihan, Luo, Xinhao, Diao, Yijia, Guo, Minyi, Zhai, Jidong, Feng, Yu, Zhang, Chen, Wu, Anbang, Leng, Jingwen
Format:	Preprint
Published:	2025
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

ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive
by: Luo, Xinhao, et al.
Published: (2025)

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

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

UniEP: Unified Expert-Parallel MoE MegaKernel for LLM Training
by: Zheng, Size, et al.
Published: (2026)

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

RedFuser: An Automatic Operator Fusion Framework for Cascaded Reductions on AI Accelerators
by: Tang, Xinsheng, et al.
Published: (2026)

Towards Compute-Aware In-Switch Computing for LLMs Tensor-Parallelism on Multi-GPU Systems
by: Zhang, Chen, et al.
Published: (2026)

MoE-Hub: Taming Software Complexity for Seamless MoE Overlap with Hardware-Accelerated Communication on Multi-GPU Systems
by: Zhou, Zhuoshan, et al.
Published: (2026)

Accelerating MoE with Dynamic In-Switch Computing on Multi-GPUs
by: Zhang, Qijun, et al.
Published: (2026)

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)

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

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

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

FlashSketch: Sketch-Kernel Co-Design for Fast Sparse Sketching on GPUs
by: Dwaraknath, Rajat Vadiraj, et al.
Published: (2026)

FastDecode: High-Throughput GPU-Efficient LLM Serving using Heterogeneous Pipelines
by: He, Jiaao, et al.
Published: (2024)

MCFuser: High-Performance and Rapid Fusion of Memory-Bound Compute-Intensive Operators
by: Zhang, Zheng, et al.
Published: (2025)

Topology-Aware Virtualization over Inter-Core Connected Neural Processing Units
by: Feng, Dahu, et al.
Published: (2025)

Scaling Deep Learning Computation over the Inter-Core Connected Intelligence Processor with T10
by: Liu, Yiqi, et al.
Published: (2024)

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

Chameleon: Taming Dynamic Operator Sequences for Memory-Intensive LLM Training
by: Wang, Zibo, et al.
Published: (2025)

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

A Flexible Programmable Pipeline Parallelism Framework for Efficient DNN Training
by: Jiang, Lijuan, et al.
Published: (2025)

Triton-distributed: Programming Overlapping Kernels on Distributed AI Systems with the Triton Compiler
by: Zheng, Size, et al.
Published: (2025)

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

Can Tensor Cores Benefit Memory-Bound Kernels? (No!)
by: Zhang, Lingqi, et al.
Published: (2025)

ZeroPP: Unleashing Exceptional Parallelism Efficiency through Tensor-Parallelism-Free Methodology
by: Tang, Ding, et al.
Published: (2024)

HadaCore: Tensor Core Accelerated Hadamard Transform Kernel
by: Agarwal, Krish, et al.
Published: (2024)

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

Kairos: Low-latency Multi-Agent Serving with Shared LLMs and Excessive Loads in the Public Cloud
by: Chen, Jinyuan, et al.
Published: (2025)

FastCache: Optimizing Multimodal LLM Serving through Lightweight KV-Cache Compression Framework
by: Zhu, Jianian, et al.
Published: (2025)

Flash-KMeans: Fast and Memory-Efficient Exact K-Means
by: Yang, Shuo, et al.
Published: (2026)

FlashMoE: Fast Distributed MoE in a Single Kernel
by: Aimuyo, Osayamen Jonathan, et al.
Published: (2025)

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

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models
by: Wu, Hang, et al.
Published: (2025)

GPU Kernel Optimization Beyond Full Builds: An LLM Framework with Minimal Executable Programs
by: Chu, Ruifan, et al.
Published: (2025)

Is Flash Attention Stable?
by: Golden, Alicia, et al.
Published: (2024)

Energy-aware Incremental OTA Update for Flash-based Batteryless IoT Devices
by: Wei, Wei, et al.
Published: (2024)

FlowPrefill: Decoupling Preemption from Prefill Scheduling Granularity to Mitigate Head-of-Line Blocking in LLM Serving
by: Hsieh, Chia-chi, et al.
Published: (2026)

FlashMP: Fast Discrete Transform-Based Solver for Preconditioning Maxwell's Equations on GPUs
by: Zhang, Haoyuan, et al.
Published: (2025)