Cover Image

Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hu, Qinghao, Yang, Shang, Guo, Junxian, Yao, Xiaozhe, Lin, Yujun, Gu, Yuxian, Cai, Han, Gan, Chuang, Klimovic, Ana, Han, Song
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DeltaZip: Efficient Serving of Multiple Full-Model-Tuned LLMs
by: Yao, Xiaozhe, et al.
Published: (2023)

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

ThunderServe: High-performance and Cost-efficient LLM Serving in Cloud Environments
by: Jiang, Youhe, et al.
Published: (2025)

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

LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention
by: Yang, Shang, et al.
Published: (2025)

Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs
by: Jiang, Youhe, et al.
Published: (2025)

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

RollPacker: Mitigating Long-Tail Rollouts for Fast, Synchronous RL Post-Training
by: Gao, Wei, et al.
Published: (2025)

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

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

Accelerating Long-Tail Generation in Synchronous RLHF Training via Adaptive Tensor Parallelism
by: Zhao, Long, et al.
Published: (2026)

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

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

AB-Sparse: Sparse Attention with Adaptive Block Size for Accurate and Efficient Long-Context Inference
by: Liu, Di, et al.
Published: (2026)

BurstEngine: an Efficient Distributed Framework for Training Transformers on Extremely Long Sequences of over 1M Tokens
by: Sun, Ao, et al.
Published: (2025)

Understanding GPU Resource Interference One Level Deeper
by: Elvinger, Paul, et al.
Published: (2025)

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

ResiHP: Taming LLM Training Failures with Dynamic Hybrid Parallelism
by: Ma, Tenghui, et al.
Published: (2026)

Unleashing Efficient Asynchronous RL Post-Training via Staleness-Constrained Rollout Coordination
by: Li, Haoyang, et al.
Published: (2026)

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

DéjàVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving
by: Strati, Foteini, et al.
Published: (2024)

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

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

RL in the Wild: Characterizing RLVR Training in LLM Deployment
by: Zhou, Jiecheng, et al.
Published: (2025)

Towards Affordable, Adaptive and Automatic GNN Training on CPU-GPU Heterogeneous Platforms
by: Qiao, Tong, et al.
Published: (2025)

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

HexGen: Generative Inference of Large Language Model over Heterogeneous Environment
by: Jiang, Youhe, et al.
Published: (2023)

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

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

Energy-Efficient Wireless Federated Learning via Doubly Adaptive Quantization
by: Han, Xuefeng, et al.
Published: (2024)

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference
by: Lin, Haoran, et al.
Published: (2025)

Chameleon: Adaptive Fault Tolerance for Distributed Training via Real-time Policy Selection
by: Zhou, Yuhang, et al.
Published: (2025)

MTGenRec: An Efficient Distributed Training System for Generative Recommendation Models in Meituan
by: Wang, Yuxiang, et al.
Published: (2025)

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

GreenDyGNN: Runtime-Adaptive Energy-Efficient Communication for Distributed GNN Training
by: Niam, Arefin, et al.
Published: (2026)

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

Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference
by: Li, Rongzhi, et al.
Published: (2025)

AgentFlow: Resilient Adaptive Cloud-Edge Framework for Multi-Agent Coordination
by: Chen, Ching Han, et al.
Published: (2025)

Analysis and Optimized CXL-Attached Memory Allocation for Long-Context LLM Fine-Tuning
by: Liaw, Yong-Cheng, et al.
Published: (2025)

Seq1F1B: Efficient Sequence-Level Pipeline Parallelism for Large Language Model Training
by: Sun, Ao, et al.
Published: (2024)