Cover Image

RL in the Wild: Characterizing RLVR Training in LLM Deployment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Jiecheng, Hu, Qinghao, Jin, Yuyang, Wang, Zerui, Sun, Peng, Gu, Yuzhe, Zhang, Wenwei, Zhai, Mingshu, Zhang, Xingcheng, Zhang, Weiming
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence 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

H2:Towards Efficient Large-Scale LLM Training on Hyper-Heterogeneous Cluster over 1,000 Chips
by: Tang, Ding, et al.
Published: (2025)

Efficient Training of Large Language Models on Distributed Infrastructures: A Survey
by: Duan, Jiangfei, et al.
Published: (2024)

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

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

Zeppelin: Balancing Variable-length Workloads in Data Parallel Large Model Training
by: Chen, Chang, et al.
Published: (2025)

AMSP: Reducing Communication Overhead of ZeRO for Efficient LLM Training
by: Chen, Qiaoling, et al.
Published: (2023)

Characterization of Large Language Model Development in the Datacenter
by: Hu, Qinghao, et al.
Published: (2024)

Schedule-Level Shared-Prefix Reuse for LLM RL Training
by: Li, Pengbo, et al.
Published: (2026)

Semantic-Aware Scheduling for GPU Clusters with Large Language Models
by: Wang, Zerui, et al.
Published: (2025)

LoongTrain: Efficient Training of Long-Sequence LLMs with Head-Context Parallelism
by: Gu, Diandian, et al.
Published: (2024)

InternEvo: Efficient Long-sequence Large Language Model Training via Hybrid Parallelism and Redundant Sharding
by: Chen, Qiaoling, et al.
Published: (2024)

DistFlow: A Fully Distributed RL Framework for Scalable and Efficient LLM Post-Training
by: Wang, Zhixin, et al.
Published: (2025)

A distributed system perspective on Backscatter systems: A review
by: Xiao, Tonghuan, et al.
Published: (2025)

MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM Serving
by: Duan, Jiangfei, et al.
Published: (2024)

TensorHub: Scalable and Elastic Weight Transfer for LLM RL Training
by: Ye, Chenhao, et al.
Published: (2026)

CFP: Efficient Optimization of Intra-Operator Parallelism Plans for Large Model Training
by: Hu, Weifang, et al.
Published: (2025)

Polar: Agentic RL on Any Harness at Scale
by: Xu, Binfeng, et al.
Published: (2026)

Lagom: Unleashing the Power of Communication and Computation Overlapping for Distributed LLM Training
by: Xu, Guanbin, et al.
Published: (2026)

Sailor: Automating Distributed Training over Dynamic, Heterogeneous, and Geo-distributed Clusters
by: Strati, Foteini, et al.
Published: (2025)

Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter
by: Hu, Qinghao, et al.
Published: (2025)

SPPO:Efficient Long-sequence LLM Training via Adaptive Sequence Pipeline Parallel Offloading
by: Chen, Qiaoling, et al.
Published: (2025)

Agentic AI-Driven UAV Network Deployment: An LLM-Enhanced Exact Potential Game Approach
by: Tang, Xin, et al.
Published: (2026)

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

EACO-RAG: Towards Distributed Tiered LLM Deployment using Edge-Assisted and Collaborative RAG with Adaptive Knowledge Update
by: Li, Jiaxing, et al.
Published: (2024)

PROSERVE: Unified Multi-Priority Request Scheduling for LLM Serving
by: Huang, Weizhe, et al.
Published: (2025)

TorchGT: A Holistic System for Large-scale Graph Transformer Training
by: Zhang, Meng, et al.
Published: (2024)

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

Bandwidth-Aware and Cost-Efficient Pipeline Parallel Scheduling in Geo-Distributed LLM Training
by: Zhang, Han, et al.
Published: (2026)

Accelerating Compound LLM Training Workloads with Maestro
by: Yuan, Xiulong, et al.
Published: (2026)

HetRL: Efficient Reinforcement Learning for LLMs in Heterogeneous Environments
by: He, Yongjun, et al.
Published: (2025)

Slice-Level Scheduling for High Throughput and Load Balanced LLM Serving
by: Cheng, Ke, et al.
Published: (2024)

OmniInfer: System-Wide Acceleration Techniques for Optimizing LLM Serving Throughput and Latency
by: Wang, Jun, et al.
Published: (2025)

MegatronApp: Efficient and Comprehensive Management on Distributed LLM Training
by: Zhao, Bohan, et al.
Published: (2025)

DistTrain: Addressing Model and Data Heterogeneity with Disaggregated Training for Multimodal Large Language Models
by: Zhang, Zili, et al.
Published: (2024)

ReviveMoE: Fast Recovery for Hardware Failures in Large-Scale MoE LLM Inference Deployments
by: Li, Haley, et al.
Published: (2026)

RollMux: Phase-Level Multiplexing for Disaggregated RL Post-Training
by: Wu, Tianyuan, et al.
Published: (2025)

ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production
by: Xiang, Yuxing, et al.
Published: (2025)

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

DynaTrain: Fast Online Parallelism Switching for Elastic LLM Training
by: Wang, Yuanqing, et al.
Published: (2026)

Egret: Reinforcement Mechanism for Sequential Computation Offloading in Edge Computing
by: Peng, Haosong, et al.
Published: (2024)