<p>Online evaluation of machine-learned models (model serving) is difficult to scale to large datasets. <a href="https://vespa.ai/">Vespa.ai</a> is an open source big data serving solution used to solve this problem and in use today on some of the largest such systems in the world. These systems evaluate models over millions of data points per request for hundreds of thousands of requests per second.</p><p>If you’re in Warsaw on February 27th, please join <a href="https://www.linkedin.com/in/jon-bratseth-6a6585/">Jon Bratseth</a> (Distinguished Architect, Verizon Media) at the <a href="https://bigdatatechwarsaw.eu/agenda/">Big Data Technology Warsaw Summit</a>, where he’ll share “Scalable machine-learned model serving” and answer any questions. Big Data Technology Warsaw Summit is a one-day conference with technical content focused on big data analysis, scalability, storage, and search. There will be 27 presentations and more than 500 attendees are expected.</p><p>Jon’s talk will explore the problem and architectural solution, show how Vespa can be used to achieve scalable serving of TensorFlow and <a href="https://onnx.ai/">ONNX</a> models, and present benchmarks comparing performance and scalability to TensorFlow Serving.</p><p>Hope to see you there!</p>