Cover Image

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bai, Xu, Islam, Muhammed Tawfiqul, Wang, Chen, Toosi, Adel N.
Format:	Preprint
Published:	2026
Subjects:	Distributed, Parallel, and Cluster Computing Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

REACH: Reinforcement Learning for Adaptive Microservice Rescheduling in the Cloud-Edge Continuum
by: Bai, Xu, et al.
Published: (2025)

LLM-Driven Intent-Based Privacy-Aware Orchestration Across the Cloud-Edge Continuum
by: Su, Zijie, et al.
Published: (2026)

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

ORACL: Optimized Reasoning for Autoscaling via Chain of Thought with LLMs for Microservices
by: Bai, Haoyu, et al.
Published: (2026)

iDynamics: A Configurable Emulation Framework for Evaluating Microservice Scheduling Policies under Controllable Cloud-Edge Dynamics
by: Chen, Ming, et al.
Published: (2025)

A Hybrid Reactive-Proactive Auto-scaling Algorithm for SLA-Constrained Edge Computing
by: Gupta, Suhrid, et al.
Published: (2025)

Proactive and Reactive Autoscaling Techniques for Edge Computing
by: Gupta, Suhrid, et al.
Published: (2025)

PipeFill: Using GPUs During Bubbles in Pipeline-parallel LLM Training
by: Arfeen, Daiyaan, et al.
Published: (2024)

Adaptive Management of Microservices in Dynamic Computing Environments: A Taxonomy and Future Directions
by: Chen, Ming, et al.
Published: (2026)

PipeOffload: Improving Scalability of Pipeline Parallelism with Memory Optimization
by: Wan, Xinyi, et al.
Published: (2025)

BitPipe: Bidirectional Interleaved Pipeline Parallelism for Accelerating Large Models Training
by: Wu, Houming, et al.
Published: (2024)

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

DistributedEstimator: Distributed Training of Quantum Neural Networks via Circuit Cutting
by: Singh, Prabhjot, et al.
Published: (2026)

GraphPipe: Improving Performance and Scalability of DNN Training with Graph Pipeline Parallelism
by: Jeon, Byungsoo, et al.
Published: (2024)

LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism
by: Wu, Bingyang, et al.
Published: (2024)

SkipPipe: Partial and Reordered Pipelining Framework for Training LLMs in Heterogeneous Networks
by: Blagoev, Nikolay, et al.
Published: (2025)

Collaborative Speculative Inference for Efficient LLM Inference Serving
by: Gao, Luyao, et al.
Published: (2025)

Efficient Routing of Inference Requests across LLM Instances in Cloud-Edge Computing
by: Yu, Shibo, et al.
Published: (2025)

ElasticMM: Efficient Multimodal LLMs Serving with Elastic Multimodal Parallelism
by: Liu, Zedong, et al.
Published: (2025)

TawPipe: Topology-Aware Weight Pipeline Parallelism for Accelerating Long-Context Large Models Training
by: Wu, Houming, et al.
Published: (2025)

QoS-Efficient Serving of Multiple Mixture-of-Expert LLMs Using Partial Runtime Reconfiguration
by: Imani, HamidReza, et al.
Published: (2025)

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference
by: He, Yongchao, et al.
Published: (2025)

JanusPipe: Efficient Pipeline Parallel Training for Machine Learning Interatomic Potentials
by: Wang, Hongyu, et al.
Published: (2026)

Preble: Efficient Distributed Prompt Scheduling for LLM Serving
by: Srivatsa, Vikranth, et al.
Published: (2024)

PolyServe: Efficient Multi-SLO Serving at Scale
by: Zhu, Kan, et al.
Published: (2025)

TD-Pipe: Temporally-Disaggregated Pipeline Parallelism Architecture for High-Throughput LLM Inference
by: Zhang, Hongbin, et al.
Published: (2025)

PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation
by: Butler, Branden, et al.
Published: (2024)

NestPipe: Large-Scale Recommendation Training on 1,500+ Accelerators via Nested Pipelining
by: Jiang, Zhida, et al.
Published: (2026)

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

A Tabular Schedule Abstraction for Communication-Aware Evaluation of Pipeline-Parallel LLM Training
by: Barley, Daniel, et al.
Published: (2026)

RouterWise: Joint Resource Allocation and Routing for Latency-Aware Multi-Model LLM Serving
by: Kasnavieh, Hossein Hosseini, et al.
Published: (2026)

A Readiness-Driven Runtime for Pipeline-Parallel Training under Runtime Variability
by: Liu, Ruitao, et al.
Published: (2026)

TetriServe: Efficient DiT Serving for Heterogeneous Image Generation
by: Lu, Runyu, et al.
Published: (2025)

WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM Serving
by: Lou, Chiheng, et al.
Published: (2025)

Nesterov Method for Asynchronous Pipeline Parallel Optimization
by: Ajanthan, Thalaiyasingam, et al.
Published: (2025)

MorphServe: Efficient and Workload-Aware LLM Serving via Runtime Quantized Layer Swapping and KV Cache Resizing
by: Su, Zhaoyuan, et al.
Published: (2025)

ConServe: Fine-Grained GPU Harvesting for LLM Online and Offline Co-Serving
by: Qiao, Yifan, et al.
Published: (2024)

gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling
by: Guo, Tianyu, et al.
Published: (2025)

Cost-Efficient LLM Serving in the Cloud: VM Selection with KV Cache Offloading
by: Kim, Kihyun, et al.
Published: (2025)

Enabling Efficient Serverless Inference Serving for LLM (Large Language Model) in the Cloud
by: Ghosh, Himel
Published: (2024)