Fallstudie | SF Technology Partners with HAMi to Enhance AI Efficiency and Significantly Reduce Costs with EffectiveGPU
Discover how SF Technology built EffectiveGPU based on the open-source HAMi framework, deeply integrating heterogeneous computing virtualization and efficient scheduling capabilities to achieve production deployment in key scenarios like AI large model inference and voice recognition, significantly improving GPU utilization and realizing cost reduction and efficiency enhancement while promoting HAMi open-source ecosystem development.
Unternehmensuebersicht
SF Technology is the technology arm of SF Express, one of China's leading logistics companies. As a technology-driven enterprise, SF Technology focuses on developing innovative solutions for logistics, AI, and cloud computing services.
领先的物流科技服务提供商
广泛的 AI 和机器学习应用
大规模 GPU 基础设施需求
专注于成本优化和效率提升
SF Technology
Fuehrender Logistiktechnologie-Anbieter in China
Traditional GPU Management Challenges
Traditional GPU usage patterns (such as whole-card exclusive allocation) led to GPUs being underutilized in inference and other light-load scenarios, resulting in serious resource waste.
资源利用率低
调度粒度粗
异构适配困难
影响 ROI
Breaking Through with EffectiveGPU Technology Practice
Facing these challenges, SF Technology's team launched the EffectiveGPU technology solution based on the open-source heterogeneous computing scheduling framework HAMi, combined with their own business scenario requirements.
The goal is to build an efficient, flexible, and unified GPU resource pooling and scheduling management system to solve problems of low resource utilization and management complexity.
GPU 池化与虚拟化
将分散的 GPU 资源整合为统一的资源池
细粒度资源切分
支持按核心利用率和显存容量进行精确切分
弹性资源超配
引入双维度超分技术
统一管理与调度
提供统一的调度接口
Significant Results: Substantial Improvement in Resource Utilization and Cost Reduction
The solution has completed multi-scenario deployment on SF Technology's AI platform, achieving remarkable results.
大模型推理服务
28 张卡 → 65 个服务
节省 37 张卡
测试服务集群
6 张卡 → 19 个服务
节省 13 张卡
性能影响
仅下降 0.5%
添加池化层后的性能影响
Tiefe Integration mit dem HAMi-Oekosystem, Aufbau effizienter Computing-Infrastruktur
Der erfolgreiche Einsatz der EffectiveGPU-Technologie ist untrennbar mit der tiefen Integration in das Open-Source-Framework HAMi verbunden.
深度集成了 HAMi 核心能力
构建了统一的抽象驱动框架
采用了兼容 HAMi 生态的设计
Validierung des HAMi-Werts, Foerderung der Reife heterogener Computing-Planung
Der erfolgreiche EffectiveGPU-Einsatz von SF Technology ist eine weitere ueberzeugende Validierung der technischen Konzepte von HAMi.
证明 HAMi 关键能力
CNCF Sandbox 项目实践
“Durch die enge Zusammenarbeit mit der HAMi-Open-Source-Community hat EffectiveGPU uns geholfen, die GPU-Ressourceneffizienz erheblich zu verbessern.”
Zukunftsausblick
SF Technology hat die Kernprobleme des GPU-Ressourcenmanagements durch die EffectiveGPU-Loesung auf Basis von HAMi effektiv geloest.