Location: Room L1 – Lotus Jr (Level 4)
Abstract: Organizations of all sizes are looking for AI infrastructure solutions to accelerate their generative AI initiatives. The rapid growth of AI is driving a massive increase in computing power and network speeds, creating high demands on storage. While NVIDIA GPUs offer scalable and efficient computing power, they need fast access to data. To solve this, NVIDIA and WEKA have partnered to create a high-performance, scalable AI solution for everyone. WEKA has launched WARRP, a flexible, infrastructure-independent blueprint for deploying high-performance Retrieval-Augmented Generation (RAG) applications. WARRP is built for scalability and efficiency, easily integrating with major cloud platforms like AWS and tools like NVIDIA NIMs and Kubernetes. This workshop will dive into the architecture and how it provides excellent linear scaling for training workloads, using WARRP with the WEKA and NVIDIA ecosystem both on-premises and in AWS with SageMaker HyperPod.
