Desiderata for next generation of ML model serving
It addresses the problem of improving ML infrastructure for developers and organizations, but is incremental as it builds on existing frameworks.
The paper identifies key qualities for next-generation machine learning inference platforms, proposing data-centricity as a design pattern to enable smarter deployment and operation at scale.
Inference is a significant part of ML software infrastructure. Despite the variety of inference frameworks available, the field as a whole can be considered in its early days. This position paper puts forth a range of important qualities that next generation of inference platforms should be aiming for. We present our rationale for the importance of each quality, and discuss ways to achieve it in practice. We propose to focus on data-centricity as the overarching design pattern which enables smarter ML system deployment and operation at scale.