用无服务器函数并行处理，让大模型推理更快更省成本。
Scalable and Cost-Efficient ML Inference: Parallel Batch Processing with Serverless Functions
- 将单体推理拆分为并行函数，动态分配资源
- 在相同成本下，执行时间减少95%以上
- 适合资源受限环境下的大规模模型推理
随着数据密集型应用的发展，有限资源环境中的批处理面临可扩展性和资源管理挑战。无服务器计算提供了一种灵活的替代方案，支持动态资源分配和自动扩展。本文探讨了如何通过将单体处理流程分解为并行函数，利用无服务器架构实现大规模机器学习推理的提速与降本。以DistilBERT模型在IMDb数据集上的情感分析为例，实验表明，相较于传统单体方法，该方案可在相同成本下将执行时间降低超过95%。
原文摘要 · Abstract (English)
As data-intensive applications grow, batch processing in limited-resource environments faces scalability and resource management challenges. Serverless computing offers a flexible alternative, enabling dynamic resource allocation and automatic scaling. This paper explores how serverless architectures can make large-scale ML inference tasks faster and cost-effective by decomposing monolithic processes into parallel functions. Through a case study on sentiment analysis using the DistilBERT model and the IMDb dataset, we demonstrate that serverless parallel processing can reduce execution time by over 95% compared to monolithic approaches, at the same cost.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。