Copertina

MAS-Attention: Memory-Aware Stream Processing for Attention Acceleration on Resource-Constrained Edge Devices

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Shakerdargah, Mohammadali, Lu, Shan, Gao, Chao, Niu, Di
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Distributed, Parallel, and Cluster Computing Artificial Intelligence Performance C.1.4; I.2.7; I.5.1
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Rotary GPU: Exploring Local Execution Paths for Large Mixture-of-Experts Models Under Limited GPU Memory
di: Jo, Myeong Jun
Pubblicazione: (2026)

Parallelization Strategies for Dense LLM Deployment: Navigating Through Application-Specific Tradeoffs and Bottlenecks
di: Topcu, Burak, et al.
Pubblicazione: (2026)

POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference
di: Kamath, Aditya K, et al.
Pubblicazione: (2024)

Towards Building Private LLMs: Exploring Multi-Node Expert Parallelism on Apple Silicon for Mixture-of-Experts Large Language Model
di: Chen, Mu-Chi, et al.
Pubblicazione: (2025)

Comparative Analysis of Large Language Model Inference Serving Systems: A Performance Study of vLLM and HuggingFace TGI
di: Kolluru, Saicharan
Pubblicazione: (2025)

SparkAttention: High-Performance Multi-Head Attention for Large Models on Volta GPU Architecture
di: Xu, Youxuan, et al.
Pubblicazione: (2025)

Collaborative Processing for Multi-Tenant Inference on Memory-Constrained Edge TPUs
di: Ng, Nathan, et al.
Pubblicazione: (2026)

Optimizing edge AI models on HPC systems with the edge in the loop
di: Aach, Marcel, et al.
Pubblicazione: (2025)

ATTNChecker: Highly-Optimized Fault Tolerant Attention for Large Language Model Training
di: Liang, Yuhang, et al.
Pubblicazione: (2024)

Benchmarking Catastrophic Forgetting Mitigation Methods in Federated Time Series Forecasting
di: Hallak, Khaled, et al.
Pubblicazione: (2025)

Vectorized Adaptive Histograms for Sparse Oblique Forests
di: Lubonja, Ariel, et al.
Pubblicazione: (2026)

Libra: Unleashing GPU Heterogeneity for High-Performance Sparse Matrix Multiplication
di: Shi, Jinliang, et al.
Pubblicazione: (2025)

MATCH: Model-Aware TVM-based Compilation for Heterogeneous Edge Devices
di: Hamdi, Mohamed Amine, et al.
Pubblicazione: (2024)

Reducing the GPU Memory Bottleneck with Lossless Compression for ML -- Extended
di: Kamath, Aditya K, et al.
Pubblicazione: (2026)

Efficient Construction of Large Search Spaces for Auto-Tuning
di: Willemsen, Floris-Jan, et al.
Pubblicazione: (2025)

Flash-Fusion: Enabling Expressive, Low-Latency Queries on IoT Sensor Streams with LLMs
di: Patherya, Kausar, et al.
Pubblicazione: (2025)

GVE-Louvain: Fast Louvain Algorithm for Community Detection in Shared Memory Setting
di: Sahu, Subhajit
Pubblicazione: (2023)

GVE-Leiden: Fast Leiden Algorithm for Community Detection in Shared Memory Setting
di: Sahu, Subhajit
Pubblicazione: (2023)

GVE-LPA: Fast Label Propagation Algorithm (LPA) for Community Detection in Shared Memory Setting
di: Sahu, Subhajit
Pubblicazione: (2023)

Token Arena: A Continuous Benchmark Unifying Energy and Cognition in AI Inference
di: Gao, Yuxuan, et al.
Pubblicazione: (2026)

SLO-Guard: Crash-Aware, Budget-Consistent Autotuning for SLO-Constrained LLM Serving
di: Lysenstøen, Christian
Pubblicazione: (2026)

Predictive Multi-Tier Memory Management for KV Cache in Large-Scale GPU Inference
di: Ganjihal, Sanjeev Rao
Pubblicazione: (2026)

HeteGen: Heterogeneous Parallel Inference for Large Language Models on Resource-Constrained Devices
di: Zhao, Xuanlei, et al.
Pubblicazione: (2024)

StreamIndex: Memory-Bounded Compressed Sparse Attention via Streaming Top-k
di: Jaber, Jaber, et al.
Pubblicazione: (2026)

DAGER: Exact Gradient Inversion for Large Language Models
di: Petrov, Ivo, et al.
Pubblicazione: (2024)

Cross-Platform Fused MoE Dispatch in Triton: Portable Expert Routing Without CUDA
di: Mitra, Subhadip
Pubblicazione: (2026)

Prima.cpp: Fast 30-70B LLM Inference on Heterogeneous and Low-Resource Home Clusters
di: Li, Zonghang, et al.
Pubblicazione: (2025)

Bine Trees: Enhancing Collective Operations by Optimizing Communication Locality
di: De Sensi, Daniele, et al.
Pubblicazione: (2025)

Parameter-Efficient and Personalized Federated Training of Generative Models at the Edge
di: Khan, Kabir, et al.
Pubblicazione: (2025)

Challenging Portability Paradigms: FPGA Acceleration Using SYCL and OpenCL
di: de Castro, Manuel, et al.
Pubblicazione: (2024)

Performance Optimization in Stream Processing Systems: Experiment-Driven Configuration Tuning for Kafka Streams
di: Chen, David, et al.
Pubblicazione: (2026)

ParaQAOA: Efficient Parallel Divide-and-Conquer QAOA for Large-Scale Max-Cut Problems Beyond 10,000 Vertices
di: Huang, Po-Hsuan, et al.
Pubblicazione: (2026)

An Incrementally Expanding Approach for Updating PageRank on Dynamic Graphs
di: Sahu, Subhajit
Pubblicazione: (2024)

Optimization of a Radiofrequency Ablation FEM Application Using Parallel Sparse Solvers
di: Miletto, Marcelo Cogo, et al.
Pubblicazione: (2024)

DF* PageRank: Improved Incrementally Expanding Approaches for Updating PageRank on Dynamic Graphs
di: Sahu, Subhajit
Pubblicazione: (2024)

Lock-Free Computation of PageRank in Dynamic Graphs
di: Sahu, Subhajit
Pubblicazione: (2024)

Tempo: Compiled Dynamic Deep Learning with Symbolic Dependence Graphs
di: Silvestre, Pedro F., et al.
Pubblicazione: (2025)

Multi-Dimensional Autoscaling of Stream Processing Services on Edge Devices
di: Sedlak, Boris, et al.
Pubblicazione: (2025)

FedMon: Federated eBPF Monitoring for Distributed Anomaly Detection in Multi-Cluster Cloud Environments
di: Zehra, Sehar, et al.
Pubblicazione: (2025)

SGDRC: Software-Defined Dynamic Resource Control for Concurrent DNN Inference on NVIDIA GPUs
di: Zhang, Yongkang, et al.
Pubblicazione: (2024)