Machine learning (ML) prediction APIs are increasingly widely used. An ML API
can change over time due to model updates or retraining. This presents a key
challenge in the usage of the API because it is often not clear to the user if
and how the ML model ... (more…)
Read more »
Dynamic shape computations have become critical in modern machine learning workloads, especially in emerging large language models. The success of these models has driven demand for deploying them to a diverse set of backend environments. In this paper, w... (more…)
Read more »
DBMSs need careful tuning for efficient performance on specific hardware and workloads. Yet, manual tuning by experienced admins is impractical for extensive... (more…)
Read more »
Delivering machine learning solutions is so much more than the model. Three key concepts covering version control, testing, and pipelines are the foundation for machine learning operations (MLOps) that help data science teams ship models quicker and with ... (more…)
Read more »