Copertina

HAS-GPU: Efficient Hybrid Auto-scaling with Fine-grained GPU Allocation for SLO-aware Serverless Inferences

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Gu, Jianfeng, Wang, Puxuan, Araya, Isaac David Nunez, Huang, Kai, Gerndt, Michael
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Distributed, Parallel, and Cluster Computing
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Hummingbird: SLO-Oriented GPU Preemption at Microsecond-scale
di: Hu, Tiancheng, et al.
Pubblicazione: (2026)

VersaSlot: Efficient Fine-grained FPGA Sharing with Big.Little Slots and Live Migration in FPGA Cluster
di: Gu, Jianfeng, et al.
Pubblicazione: (2025)

Apodotiko: Enabling Efficient Serverless Federated Learning in Heterogeneous Environments
di: Chadha, Mohak, et al.
Pubblicazione: (2024)

Torpor: GPU-Enabled Serverless Computing for Low-Latency, Resource-Efficient Inference
di: Yu, Minchen, et al.
Pubblicazione: (2023)

HarmonyBatch: Batching multi-SLO DNN Inference with Heterogeneous Serverless Functions
di: Chen, Jiabin, et al.
Pubblicazione: (2024)

Serving Hybrid LLM Loads with SLO Guarantees Using CPU-GPU Attention Piggybacking
di: Mo, Zizhao, et al.
Pubblicazione: (2026)

Tangram: High-resolution Video Analytics on Serverless Platform with SLO-aware Batching
di: Peng, Haosong, et al.
Pubblicazione: (2024)

SLO-aware GPU Frequency Scaling for Energy Efficient LLM Inference Serving
di: Kakolyris, Andreas Kosmas, et al.
Pubblicazione: (2024)

Towards Fast Setup and High Throughput of GPU Serverless Computing
di: Zhao, Han, et al.
Pubblicazione: (2024)

FaaSTube: Optimizing GPU-oriented Data Transfer for Serverless Computing
di: Wu, Hao, et al.
Pubblicazione: (2024)

Dependency-aware Resource Allocation for Serverless Functions at the Edge
di: Baresi, Luciano, et al.
Pubblicazione: (2023)

Dilu: Enabling GPU Resourcing-on-Demand for Serverless DL Serving via Introspective Elasticity
di: Lv, Cunchi, et al.
Pubblicazione: (2025)

ParvaGPU: Efficient Spatial GPU Sharing for Large-Scale DNN Inference in Cloud Environments
di: Lee, Munkyu, et al.
Pubblicazione: (2024)

Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism
di: Mo, Zizhao, et al.
Pubblicazione: (2025)

Taming GPU Underutilization via Static Partitioning and Fine-grained CPU Offloading
di: Schieffer, Gabin, et al.
Pubblicazione: (2026)

Training Heterogeneous Client Models using Knowledge Distillation in Serverless Federated Learning
di: Chadha, Mohak, et al.
Pubblicazione: (2024)

KIS-S: A GPU-Aware Kubernetes Inference Simulator with RL-Based Auto-Scaling
di: Zhang, Guilin, et al.
Pubblicazione: (2025)

HybridGen: Efficient LLM Generative Inference via CPU-GPU Hybrid Computing
di: Lin, Mao, et al.
Pubblicazione: (2026)

gFaaS: Enabling Generic Functions in Serverless Computing
di: Chadha, Mohak, et al.
Pubblicazione: (2024)

Frenzy: A Memory-Aware Serverless LLM Training System for Heterogeneous GPU Clusters
di: Chang, Zihan, et al.
Pubblicazione: (2024)

MQFQ-Sticky: Fair Queueing For Serverless GPU Functions
di: Fuerst, Alexander, et al.
Pubblicazione: (2025)

SLO-Aware Scheduling for Large Language Model Inferences
di: Huang, Jinqi, et al.
Pubblicazione: (2025)

Evaluation of Programming Models and Performance for Stencil Computation on Current GPU Architectures
di: Shan, Baodi, et al.
Pubblicazione: (2024)

Accelerating Drug Discovery in AutoDock-GPU with Tensor Cores
di: Schieffer, Gabin, et al.
Pubblicazione: (2024)

Efficient CPU-GPU Collaborative Inference for MoE-based LLMs on Memory-Limited Systems
di: Huang, En-Ming, et al.
Pubblicazione: (2025)

Cost-Performance Analysis: A Comparative Study of CPU-Based Serverless and GPU-Based Training Architectures
di: Barrak, Amine, et al.
Pubblicazione: (2025)

An Efficient, Reliable and Observable Collective Communication Library in Large-scale GPU Training Clusters
di: Zhang, Mingjun, et al.
Pubblicazione: (2025)

HarMoEny: Efficient Multi-GPU Inference of MoE Models
di: Doucet, Zachary, et al.
Pubblicazione: (2025)

Fantasy: Efficient Large-scale Vector Search on GPU Clusters with GPUDirect Async
di: Liu, Yi, et al.
Pubblicazione: (2025)

The Fused Kernel Library: A C++ API to Develop Highly-Efficient GPU Libraries
di: Amoros, Oscar, et al.
Pubblicazione: (2025)

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

GMLake: Efficient and Transparent GPU Memory Defragmentation for Large-scale DNN Training with Virtual Memory Stitching
di: Guo, Cong, et al.
Pubblicazione: (2024)

HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference
di: Zhong, Shuzhang, et al.
Pubblicazione: (2025)

A Framework for Fine-Grained Synchronization of Dependent GPU Kernels
di: Jangda, Abhinav, et al.
Pubblicazione: (2023)

Towards Resource-Efficient Serverless LLM Inference with SLINFER
di: Xu, Chuhao, et al.
Pubblicazione: (2025)

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference
di: He, Yongchao, et al.
Pubblicazione: (2025)

GICC: A High-Performance Runtime for GPU-Initiated Communication and Coordination in Modern HPC Systems
di: Shan, Baodi, et al.
Pubblicazione: (2026)

GPU-Accelerated Distributed QAOA on Large-scale HPC Ecosystems
di: Xu, Zhihao, et al.
Pubblicazione: (2025)

Breaking the Memory Wall: A Study of I/O Patterns and GPU Memory Utilization for Hybrid CPU-GPU Offloaded Optimizers
di: Maurya, Avinash, et al.
Pubblicazione: (2024)

Affinity-aware Serverless Function Scheduling
di: De Palma, Giuseppe, et al.
Pubblicazione: (2024)