Cover Image

CoCoDiff: Optimizing Collective Communications for Distributed Diffusion Transformer Inference Under Ulysses Sequence Parallelism

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ma, Bin, Ding, Xingjian, Bicer, Tekin, Su, Pengfei, Li, Dong
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

mLR: Scalable Laminography Reconstruction based on Memoization
by: Ma, Bin, et al.
Published: (2025)

SwiftFusion: Scalable Sequence Parallelism for Distributed Inference of Diffusion Transformers on GPUs
by: Yang, Jiacheng, et al.
Published: (2026)

CoCoI: Distributed Coded Inference System for Straggler Mitigation
by: Liu, Xing, et al.
Published: (2025)

Staleness-Centric Optimizations for Parallel Diffusion MoE Inference
by: Luo, Jiajun, et al.
Published: (2024)

Untied Ulysses: Memory-Efficient Context Parallelism via Headwise Chunking
by: Ghadia, Ravi, et al.
Published: (2026)

Mist: Efficient Distributed Training of Large Language Models via Memory-Parallelism Co-Optimization
by: Zhu, Zhanda, et al.
Published: (2025)

Distributed Generative Inference of LLM at Internet Scales with Multi-Dimensional Communication Optimization
by: Chen, Jiu, et al.
Published: (2026)

Joint Optimization of Offloading, Batching and DVFS for Multiuser Co-Inference
by: Xu, Yaodan, et al.
Published: (2025)

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

ChunkFlow: Communication-Aware Chunked Prefetching for Layerwise Offloading in Distributed Diffusion Transformer Inference
by: Meng, Han, et al.
Published: (2026)

Semantic Parallelism: Redefining Efficient MoE Inference via Model-Data Co-Scheduling
by: Li, Yan, et al.
Published: (2025)

Folding Tensor and Sequence Parallelism for Memory-Efficient Transformer Training & Inference
by: Shyam, Vasu, et al.
Published: (2026)

POLAR-PIC: A Holistic Framework for Matrixized PIC with Co-Designed Compute, Layout, and Communication
by: Rao, Yizhuo, et al.
Published: (2026)

Amoeba: Runtime Tensor Parallel Transformation for LLM Inference Services
by: Chen, Haoyu, et al.
Published: (2025)

HelixPipe: Efficient Distributed Training of Long Sequence Transformers with Attention Parallel Pipeline Parallelism
by: Zhang, Geng, et al.
Published: (2025)

Learning to Shard: RL for Co-optimizing the Parallelism Degrees and Per-operator Sharding Dimensions in Distributed LLM Inference
by: Yin, Ruokai, et al.
Published: (2025)

Hiding Communication Cost in Distributed LLM Training via Micro-batch Co-execution
by: Wang, Haiquan, et al.
Published: (2024)

Steering a Fleet: Adaptation for Large-Scale, Workflow-Based Experiments
by: Pruyne, Jim, et al.
Published: (2024)

PROBE: Co-Balancing Computation and Communication in MoE Inference via Real-Time Predictive Prefetching
by: Zhu, Qianchao, et al.
Published: (2026)

Optimizing Long-context LLM Serving via Fine-grained Sequence Parallelism
by: Li, Cong, et al.
Published: (2025)

Communication-Efficient Serving for Video Diffusion Models with Latent Parallelism
by: Wu, Zhiyuan, et al.
Published: (2025)

COSMIC: Enabling Full-Stack Co-Design and Optimization of Distributed Machine Learning Systems
by: Raju, Aditi, et al.
Published: (2025)

Hybrid-Parallel: Achieving High Performance and Energy Efficient Distributed Inference on Robots
by: Sun, Zekai, et al.
Published: (2024)

MixServe: An Automatic Distributed Serving System for MoE Models with Hybrid Parallelism Based on Fused Communication Algorithm
by: Zhou, Bowen, et al.
Published: (2026)

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

StarTrail: Concentric Ring Sequence Parallelism for Efficient Near-Infinite-Context Transformer Model Training
by: Liu, Ziming, et al.
Published: (2024)

COPUS: Co-adaptive Parallelism and Batch Size Selection in Large Language Model Training
by: Sakip, Akhmed, et al.
Published: (2026)

Hydraulis: Balancing Large Transformer Model Training via Co-designing Parallel Strategies and Data Assignment
by: Li, Haoyang, et al.
Published: (2024)

xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
by: Fang, Jiarui, et al.
Published: (2024)

Distributed Inference Performance Optimization for LLMs on CPUs
by: He, Pujiang, et al.
Published: (2024)

A HPX Communication Benchmark: Distributed FFT using Collectives
by: Strack, Alexander, et al.
Published: (2025)

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

Characterizing Communication Patterns in Distributed Large Language Model Inference
by: Xu, Lang, et al.
Published: (2025)

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

GENSERVE: Efficient Co-Serving of Heterogeneous Diffusion Model Workloads
by: Ye, Fanjiang, et al.
Published: (2026)

Sutradhara: An Intelligent Orchestrator-Engine Co-design for Tool-based Agentic Inference
by: Biswas, Anish, et al.
Published: (2026)

DSP: Dynamic Sequence Parallelism for Multi-Dimensional Transformers
by: Zhao, Xuanlei, et al.
Published: (2024)

FPTC: A Fast Parallel Transform-based Codec for Efficient Asymmetric Signal Compression
by: Mechels, Ben, et al.
Published: (2026)

Optimizing Distributed ML Communication with Fused Computation-Collective Operations
by: Punniyamurthy, Kishore, et al.
Published: (2023)

Optimizing Communication in Byzantine Agreement Protocols with Slim-HBBFT
by: Sony, Nasit S, et al.
Published: (2025)