Scaling AI systems: where theory meets constraint

As demand for large scale AI systems grows, the limiting factor is no longer model capability, but compute availability, efficiency, and system design. Lambda cofounder/CEO Stephen Balaban and Gradient General Partner Zach Bratun-Glennon will examine how modern workloads interact with real-world compute constraints and the software investment and developments taking place to get the most out of cutting edge GPUs. They’ll unpack where training and inference workloads diverge in their infrastructure requirements, the practical limits of GPU utilization and what drives underperformance, and what we can expect to see next in AI infrastructure as constraints continue to evolve. Speakers: Zach Bratun-Glennon — Gradient; Stephen Balaban — Lambda.