Paper accepted at CAIN 2024 conference

Authors: Francisco Durán, Silverio Martínez Fernández, Matias Martinez, and Patricia Lago.

This study dives into ML serving architectural design decisions for the purpose of understanding and identifying them with respect to quality characteristics from the point of view of researchers and practitioners in the context of ML serving literature.

Our research questions:
RQ1: What are the ADDs of ML serving?
RQ2: What are the studied quality characteristics of those ADDs?

This preliminary study is the first step in our goal to achieve green ML serving. Our analysis may aid ML researchers and practitioners in making green-aware architecture design decisions when serving their models.

Paper: https://arxiv.org/pdf/2402.07585.pdf