Image de couverture de livre

SAIR: Cost-Efficient Multi-Stage ML Pipeline Autoscaling via In-Context Reinforcement Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Su, Jianchang, Zhang, Yifan, Lin, Shengkai, Zhao, Shizhen, Zheng, Yusheng, Yang, Yiwei, Zhang, Wei
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Distributed, Parallel, and Cluster Computing
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

LiveR: Fine-Grained Elasticity via Live Reconfiguration for Model Training
par: Liu, Haoyuan, et autres
Publié: (2026)

SpotKube: Cost-Optimal Microservices Deployment with Cluster Autoscaling and Spot Pricing
par: Edirisinghe, Dasith, et autres
Publié: (2024)

Multi-Objective Optimization of Consumer Group Autoscaling in Message Broker Systems
par: Landau, Diogo, et autres
Publié: (2024)

An SLO Driven and Cost-Aware Autoscaling Framework for Kubernetes
par: Punniyamoorthy, Vinoth, et autres
Publié: (2025)

Bandwidth-Aware and Cost-Efficient Pipeline Parallel Scheduling in Geo-Distributed LLM Training
par: Zhang, Han, et autres
Publié: (2026)

Self-adaptive, Requirements-driven Autoscaling of Microservices
par: Nunes, João Paulo Karol Santos, et autres
Publié: (2024)

Proactive and Reactive Autoscaling Techniques for Edge Computing
par: Gupta, Suhrid, et autres
Publié: (2025)

TokenScale: Timely and Accurate Autoscaling for Disaggregated LLM Serving with Token Velocity
par: Lai, Ruiqi, et autres
Publié: (2025)

ENOVA: Autoscaling towards Cost-effective and Stable Serverless LLM Serving
par: Huang, Tao, et autres
Publié: (2024)

FEPLB: Exploiting Copy Engines for Nearly Free MoE Load Balancing in Distributed Training
par: Qi, Shuyao, et autres
Publié: (2026)

Declarative Data Pipeline for Large Scale ML Services
par: Yang, Yunzhao, et autres
Publié: (2025)

ORACL: Optimized Reasoning for Autoscaling via Chain of Thought with LLMs for Microservices
par: Bai, Haoyu, et autres
Publié: (2026)

TridentServe: A Stage-level Serving System for Diffusion Pipelines
par: Xia, Yifei, et autres
Publié: (2025)

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference
par: He, Yongchao, et autres
Publié: (2025)

Daedalus: Self-Adaptive Horizontal Autoscaling for Resource Efficiency of Distributed Stream Processing Systems
par: Pfister, Benjamin J. J., et autres
Publié: (2024)

EPS-MoE: Expert Pipeline Scheduler for Cost-Efficient MoE Inference
par: Qian, Yulei, et autres
Publié: (2024)

Loki: A System for Serving ML Inference Pipelines with Hardware and Accuracy Scaling
par: Ahmad, Sohaib, et autres
Publié: (2024)

BLITZSCALE: Fast and Live Large Model Autoscaling with O(1) Host Caching
par: Zhang, Dingyan, et autres
Publié: (2024)

HetGPU: The pursuit of making binary compatibility towards GPUs
par: Yang, Yiwei, et autres
Publié: (2025)

HGraphScale: Hierarchical Graph Learning for Autoscaling Microservice Applications in Container-based Cloud Computing
par: Fang, Zhengxin, et autres
Publié: (2025)

LSRAM: A Lightweight Autoscaling and SLO Resource Allocation Framework for Microservices Based on Gradient Descent
par: Hu, Kan, et autres
Publié: (2024)

SPPO:Efficient Long-sequence LLM Training via Adaptive Sequence Pipeline Parallel Offloading
par: Chen, Qiaoling, et autres
Publié: (2025)

Efficient Long Context Fine-tuning with Chunk Flow
par: Yuan, Xiulong, et autres
Publié: (2025)

MPipeMoE: Memory Efficient MoE for Pre-trained Models with Adaptive Pipeline Parallelism
par: Zhang, Zheng, et autres
Publié: (2025)

TD-Pipe: Temporally-Disaggregated Pipeline Parallelism Architecture for High-Throughput LLM Inference
par: Zhang, Hongbin, et autres
Publié: (2025)

LA-IMR: Latency-Aware, Predictive In-Memory Routing and Proactive Autoscaling for Tail-Latency-Sensitive Cloud Robotics
par: Seo, Eunil, et autres
Publié: (2025)

Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference
par: Li, Rongzhi, et autres
Publié: (2025)

Cicada: A Pipeline-Efficient Approach to Serverless Inference with Decoupled Management
par: Wu, Z., et autres
Publié: (2025)

The High Cost of Keeping Warm: Characterizing Overhead in Serverless Autoscaling Policies
par: Kondrashov, Leonid, et autres
Publié: (2025)

Seq1F1B: Efficient Sequence-Level Pipeline Parallelism for Large Language Model Training
par: Sun, Ao, et autres
Publié: (2024)

A Pipelined Collaborative Speculative Decoding Framework for Efficient Edge-Cloud LLM Inference
par: Zhang, Yida, et autres
Publié: (2026)

NCCLbpf: Verified, Composable Policy Execution for GPU Collective Communication
par: Zheng, Yusheng
Publié: (2026)

Hierarchical Autoscaling for Large Language Model Serving with Chiron
par: Patke, Archit, et autres
Publié: (2025)

PARD: Enhancing Goodput for Inference Pipeline via Proactive Request Dropping
par: Zhao, Zhixin, et autres
Publié: (2026)

Multi-Modal Style Transfer-based Prompt Tuning for Efficient Federated Domain Generalization
par: Chen, Yuliang, et autres
Publié: (2026)

CASA: A Framework for SLO and Carbon-Aware Autoscaling and Scheduling in Serverless Cloud Computing
par: Qi, S., et autres
Publié: (2024)

PipeSD: An Efficient Cloud-Edge Collaborative Pipeline Inference Framework with Speculative Decoding
par: Han, Yunhe, et autres
Publié: (2026)

MAS-H2: A Hierarchical Multi-Agent System for Holistic Cloud-Native Autoscaling
par: Hamzeh, Hamed, et autres
Publié: (2026)

Adaptra: Straggler-Resilient Hybrid-Parallel Training with Pipeline Adaptation
par: Wu, Tianyuan, et autres
Publié: (2025)

DawnPiper: A Memory-scablable Pipeline Parallel Training Framework
par: Peng, Xuan, et autres
Publié: (2025)