Cover Image

Stream-CQSA: Avoiding Out-of-Memory in Attention Computation via Flexible Workload Scheduling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bian, Yiming, Akey, Joshua M.
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Distributed, Parallel, and Cluster Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Prioritizing Modalities: Flexible Importance Scheduling in Federated Multimodal Learning
by: Bian, Jieming, et al.
Published: (2024)

Prediction-Assisted Online Distributed Deep Learning Workload Scheduling in GPU Clusters
by: Luo, Ziyue, et al.
Published: (2025)

Priority-Aware Preemptive Scheduling for Mixed-Priority Workloads in MoE Inference
by: Siavashi, Mohammad, et al.
Published: (2025)

Agent.xpu: Efficient Scheduling of Agentic LLM Workloads on Heterogeneous SoC
by: Wei, Xinming, et al.
Published: (2025)

Improving Automatic Parallel Training via Balanced Memory Workload Optimization
by: Wang, Yujie, et al.
Published: (2023)

An Advanced Reinforcement Learning Framework for Online Scheduling of Deferrable Workloads in Cloud Computing
by: Dong, Hang, et al.
Published: (2024)

FlashMem: Supporting Modern DNN Workloads on Mobile with GPU Memory Hierarchy Optimizations
by: Shu, Zhihao, et al.
Published: (2026)

DASH: Deterministic Attention Scheduling for High-throughput Reproducible LLM Training
by: Qiang, Xinwei, et al.
Published: (2026)

CloudFormer: An Attention-based Performance Prediction for Public Clouds with Unknown Workload
by: Shahbazinia, Amirhossein, et al.
Published: (2025)

Efficient Unified Caching for Accelerating Heterogeneous AI Workloads
by: Wang, Tianze, et al.
Published: (2025)

Communication-Avoiding Linear Algebraic Kernel K-Means on GPUs
by: Bellavita, Julian, et al.
Published: (2026)

Hybrid Learning and Optimization-Based Dynamic Scheduling for DL Workloads on Heterogeneous GPU Clusters
by: Dongare, Shruti, 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)

Taming Unbalanced Training Workloads in Deep Learning with Partial Collective Operations
by: Li, Shigang, et al.
Published: (2019)

xMem: A CPU-Based Approach for Accurate Estimation of GPU Memory in Deep Learning Training Workloads
by: Shi, Jiabo, et al.
Published: (2025)

ViBE: Co-Optimizing Workload Skew and Hardware Variability for MoE Serving
by: Go, Seokjin, et al.
Published: (2026)

A Heavy-Load-Enhanced and Changeable-Periodicity-Perceived Workload Prediction Network
by: Chen, Feiyi, et al.
Published: (2023)

Maya: Optimizing Deep Learning Training Workloads using GPU Runtime Emulation
by: Yarlagadda, Srihas, et al.
Published: (2025)

CARIn: Constraint-Aware and Responsive Inference on Heterogeneous Devices for Single- and Multi-DNN Workloads
by: Panopoulos, Ioannis, et al.
Published: (2024)

DALI: A Workload-Aware Offloading Framework for Efficient MoE Inference on Local PCs
by: Zhu, Zeyu, et al.
Published: (2026)

Workflow-Driven Modeling for the Compute Continuum: An Optimization Approach to Automated System and Workload Scheduling
by: Sharma, Aasish Kumar, et al.
Published: (2025)

PackInfer: Compute- and I/O-Efficient Attention for Batched LLM Inference
by: Ning, Rui, et al.
Published: (2026)

Accelerating Heterogeneous Tensor Parallelism via Flexible Workload Control
by: Wang, Zhigang, et al.
Published: (2024)

Intelligent Task Scheduling for Microservices via A3C-Based Reinforcement Learning
by: Wang, Yang, et al.
Published: (2025)

Spindle: Efficient Distributed Training of Multi-Task Large Models via Wavefront Scheduling
by: Wang, Yujie, et al.
Published: (2024)

FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices using a Computing Power Aware Scheduler
by: Li, Zilinghan, et al.
Published: (2023)

StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation
by: Zhong, Yinmin, et al.
Published: (2025)

DeFRiS: Silo-Cooperative IoT Applications Scheduling via Decentralized Federated Reinforcement Learning
by: Wang, Zhiyu, et al.
Published: (2026)

Enabling Disaggregated Multi-Stage MLLM Inference via GPU-Internal Scheduling and Resource Sharing
by: Zhao, Lingxiao, et al.
Published: (2025)

Arena: Efficiently Training Large Models via Dynamic Scheduling and Adaptive Parallelism Co-Design
by: Xue, Chunyu, et al.
Published: (2024)

LIBRA: Enabling Workload-aware Multi-dimensional Network Topology Optimization for Distributed Training of Large AI Models
by: Won, William, et al.
Published: (2021)

Collaborative Resource Management and Workloads Scheduling in Cloud-Assisted Mobile Edge Computing across Timescales
by: Tang, Lujie, et al.
Published: (2024)

The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project
by: Chen, Huamin, et al.
Published: (2026)

Eventually-Consistent Federated Scheduling for Data Center Workloads
by: Thiyyakat, Meghana, et al.
Published: (2023)

FlexSP: Accelerating Large Language Model Training via Flexible Sequence Parallelism
by: Wang, Yujie, et al.
Published: (2024)

Locality-aware Fair Scheduling in LLM Serving
by: Cao, Shiyi, et al.
Published: (2025)

Aryl: An Elastic Cluster Scheduler for Deep Learning
by: Li, Jiamin, et al.
Published: (2022)

Learning to Schedule Online Tasks with Bandit Feedback
by: Xu, Yongxin, et al.
Published: (2024)

SkipPredict: When to Invest in Predictions for Scheduling
by: Shahout, Rana, et al.
Published: (2024)

Scheduling for On-Board Federated Learning with Satellite Clusters
by: Razmi, Nasrin, et al.
Published: (2024)