FMS 2026 Speaker Session with Supermicro

AI inference is breaking the old rules of storage.

As context windows grow, agent sessions multiply, and concurrent users scale, KV cache is emerging as the real performance bottleneck for LLM inference. Traditional storage architectures weren't built for this shift. At FMS 2026, Graid Technology is teaming up with Supermicro to unpack how to build AI storage infrastructure that actually scales with today's inference workloads.
‍

📍 Session: AI Storage Made Better, Together: Scaling Approaches to AI Storage Infrastructure

🗓️ August 4 | 8:35 AM

📌 Santa Clara Convention Center, Mission City Ballroom

‍

Speakers:

🎙️ Randy Kreiser, Field CTO, Graid Technology

🎙️ Paul McLeod, Product Director, Storage Systems, Supermicro

‍

We'll walk through scaling approaches across every tier, from single-server to rack-scale to monolithic deployments, and show how dense NVMe GPU platforms paired with Graid Technology's SupremeRAID™ turn SSDs into a high-performance, protected KV cache tier.If storage is becoming your AI infrastructure bottleneck, this is the session to catch. See you at FMS 2026!