Serverless Architecture Patterns for Scalable Machine Learning Inference Pipelines

Autores/as

  • GAURAV KUMAR SINHA 7319 Longspur Hollow Lane Katy, TX 77493-4704, United States

DOI:

https://doi.org/10.66838/sauc.6526

Palabras clave:

Serverless Computing, Machine Learning Inference, Architecture Patterns, Cold Start Mitigation, Dynamic Batching, Event-Driven Pipelines, LoRA Adapter Serving, Cloud Cost Optimization.

Resumen

Serverless Architecture Patterns for Scalable Machine Learning Inference PipelinesServing machine learning models in production is an exercise in handling uncertainty. Traffic arrives in bursts, models differ enormously in size and cost, and demand for a given model may be near zero for hours and then jump by an order of magnitude within seconds. Serverless computing, in which a cloud provider runs short-lived functions and managed services on demand and bills only for what is used, promises to match capacity to such demand automatically. Applying it to inference is not straightforward, however, because model loading causes cold starts, functions are stateless and limited in memory and duration, and accelerators are scarce. This paper presents a catalog of eight serverless architecture patterns for machine learning inference pipelines, together with guidance on when each should be used.....

Descargas

Los datos de descargas todavía no están disponibles.

Estadísticas globales ℹ️

Totales acumulados desde su publicación
64
Visualizaciones
15
Descargas
79
Total

Descargas

Publicado

2025-05-30

Cómo citar

GAURAV KUMAR SINHA. (2025). Serverless Architecture Patterns for Scalable Machine Learning Inference Pipelines. Street Art & Urban Creativity, 11(4), 262–276. https://doi.org/10.66838/sauc.6526

Número

Sección

Artículos de investigación