Model Serving
PulseAugur coverage of Model Serving — every cluster mentioning Model Serving across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
Kubernetes for AI: Managing GPUs, Model Serving, and Scalable Inference
This article discusses the use of Kubernetes for managing AI workloads, focusing on the challenges of handling graphics processing units (GPUs), model serving, and scalable inference. It highlights that while deploying …
-
Google's TabFM deployed on Databricks Model Serving
This article provides a practical guide on how to deploy Google's TabFM, a tabular foundation model, using Databricks Model Serving. It details the process of packaging the model and setting it up as a real-time endpoin…
-
Databricks details real-time e-commerce recommendation system architecture
Databricks has detailed a reference architecture for building real-time e-commerce recommendation systems, designed to enhance personalization and conversion rates. The system leverages the Databricks Data Intelligence …
-
MLOps Focuses on Efficient Model Serving Infrastructure
This article discusses MLOps and model serving infrastructure, focusing on practical approaches to avoid wasting resources. It highlights the importance of efficient machine learning infrastructure for effective model d…
-
Databricks Feature Store achieves sub-second freshness for ML models
Databricks has enhanced its Feature Store to provide sub-second freshness for machine learning models, addressing the need for real-time data in applications like fraud detection and personalization. The updated Feature…
-
Amtrak builds AI-powered data backbone for major rail transformation
Amtrak is implementing a comprehensive digital intelligence platform called Rail Intelligence, built on Databricks, to support its most significant operational transformation in over 50 years. This platform aims to unif…
-
Databricks showcases real-time transaction scoring under 40ms
Databricks has developed a sample application that demonstrates how to process credit card transactions in milliseconds using a combination of their Model Serving and Lakebase features. The application, built with FastA…