Automating the Edge with Robotics

Cloudflare, Databricks unite to boost AI inference at the edge

Cloudflare, Databricks unite to boost AI inference at the edge

Cloudflare continues collaborating with Databricks to boost MLflow capabilities to developers on Cloudflare’s serverless developer platform.

Cloudflare aims to narrow the divide between model training and deployment by becoming a part of the open-source MLflow project. This collaboration empowers the execution of AI models near end-users, providing a low-latency experience. Leveraging AI in businesses entails multiple steps, including data collection, storage, model training and deployment for inference, to make it work seamlessly from end to end.

According to Matthew Prince, the CEO and co-founder of Cloudflare, the Workers AI platform is a groundbreaking serverless solution that allows AI deployment at the edge.

“Together with Databricks, we can offer a comprehensive and optimized platform to support a wide spectrum of AI workflows, models and applications,” adds Prince.

Databricks and Cloudflare note they already collaborate to simplify the AI lifecycle by enabling more straightforward and affordable data sharing through Delta Sharing with R2 storage. The companies say that Cloudflare’s R2 is a distributed object storage offering that allows the sharing of live data sets and AI models with Databricks, eliminating the need for complex data transfers or duplications and with zero egress fees.

By leveraging MLflow, an open-source platform for ML lifecycle management, teams can track, share and deploy models for batch or real-time inference. This collaboration enables developers to train models on Databricks’ AI platform and deploy them on Cloudflare’s global network, completing the AI lifecycle with hyper-local inferencing at the edge.

Cloudflare Workers AI developers can deploy MLflow-compatible models effortlessly on Cloudflare’s global network. With MLflow, developers can efficiently package, deploy and track models on Cloudflare’s serverless developer platform.

Cloudflare’s support for MLflow allows customers to deploy their Databricks-trained models directly to the edge, according to Craig Wiley, the senior director of AI/ML products at Databricks.

“Cloudflare’s new edge deployment capabilities expand the value of MLflow to a broad set of new use cases.”

In September, Cloudflare made headlines for introducing Cloudflare One. This suite provides data security across the web, SaaS and private applications. The technology, built on Cloudflare’s global network, addresses the modern coding risks and the increasing use of AI. By integrating various security services into a centralized system, Cloudflare One says it simplifies security management for organizations.

Article Topics

 |   |   | 


Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Featured Edge Computing Company

Edge Ecosystem Videos

Automating the Edge


Deploying AI Models at the Edge


Latest News