Skip to content
Hot eventDeveloping

IBM time-series models run natively on Confluent

1 reports1 reporting sourcesUpdated 2 h ago

Start here

AI digest

IBM's time-series foundation models now run natively inside Confluent as built-in functions, both in the cloud and on premises, according to a Hugging Face blog post. The models, which IBM says have more than 50 million downloads, execute on CPUs without GPUs, and teams use Apache Flink and SQL to apply forecasting, anomaly detection and semantic intelligence to streaming data. In Confluent Cloud the models are fully managed with nothing to deploy; on premises they run within a customer's own infrastructure via Confluent Platform for Apache Flink. The stated goal is to put model outputs in front of the applications and people responsible for the next action, with target uses in manufacturing, retail, banking and airlines, from keeping production lines in spec to assessing card payments and forecasting trading volume.

Generated from reports · updated 2 h ago

Report timeline

Follow the reports to see the event from different sides.

November 18
  1. Hugging Face Blog
    IBM Time-Series Models in Confluent Streamhouse: Real-Time Forecasting and Anomaly Detection

    IBM's time-series foundation models, with over 50 million downloads, now run natively inside Confluent as built-in functions in the cloud and on premises, executing on CPUs without GPUs. Using Apache Flink and SQL, teams can apply forecasting, anomaly detection and semantic intelligence to streaming data so model outputs reach the applications and people responsible for the next action. The models target use cases across manufacturing, retail, banking and airlines, from keeping production lines in spec to assessing card payments and forecasting trading volume.

Heat for this event

Not enough continuous observations yet to draw a trend.