Engineering
About
Vlad Shulman is a repeat founder (including retain.ai, acquired by Dagster), has experience across both product and engineering, and holds a degree in mathematics from the University of Waterloo. Vlad leads Forward Deployed Engineering at Baseten.
In this article, we outline a continuous integration and continuous deployment (CI/CD) pipeline for using AI models in production.
Multi-Instance GPUs enable splitting a single H100 GPU across two model serving instances for performance that matches or beats an A100 GPU at a 20% lower cost.
