Storage to Enable Inference at Scale - Open Storage Summit 2025 Session 4

Join us for Open Storage Summit Session 4: Storage to Enable Inference at Scale: https://www.thecube.net/events/superm... AI inference is scaling fast, which means storage infrastructure must evolve to keep up. New distributed inference frameworks and advanced storage protocols from NVIDIA, supported by Supermicro, are powering the next wave of large-scale, high-performance AI deployments. 🗣️Thanks to our partners NVIDIA, Solidigm, Cloudian, and Hammerspace for joining us for this session. Timestamps: 00:00 - Scaling AI Inference: From Supermicro Foundations to High-Volume Storage Solutions 05:25 - AI Factories: Expanding Role in Production Serving and Inference 10:38 - NVIDIA's NeMo Retriever Services for Enterprise Data 19:54 - Solidigm's Contribution to AI Infrastructures with SSDs 24:34 - The Importance of High-Performance Storage in Inference 34:15 - Object Storage and Cloudian’s Role in AI Data Platforms 44:18 - Foundations and Frontiers of AI: Integrated Solutions and Infrastructure #OpenStorageSummit #SupermicroStorage2025 #Supermicro