<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/a21f660456d74e77b28db6491847b9d9&quot; frameborder=&quot;0&quot; width=&quot;1730&quot; height=&quot;1297&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1297</height><width>1730</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1297</thumbnail_height><thumbnail_width>1730</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/a21f660456d74e77b28db6491847b9d9-00001.gif</thumbnail_url><duration>345.73333333333375</duration><title>Baseten demo</title><description>In this video, I explain what Baseten is and provide a quick demo of the product. Baseten is a machine learning infrastructure company that focuses on model inference. I discuss the three main value propositions of Baseten: auto scalability, cost efficiency of GPU usage, and the ability to avoid hiring additional MLOps and DevOps professionals. I also highlight how Baseten is used by various customers with different models and scales. Additionally, I explain the on-ramp to Baseten through the use of trusses, an open source model packaging and deployment library. Overall, this video provides an overview of Baseten and its advantages.</description></oembed>