Supermicro Open Storage Summit 2026 | Architecting AI Inference and Data Management for Maximum Scale

Video Player is loading.

Stream Type LIVE

Current Time 0:00

Loaded: 0%

Sponsors
Resources

SuperStorage® Scalable Storage Servers

Rack-scale storage systems for scale-out and scale-up software-defined storage applications including AI/ML Storage, CSP Storage and Enterprise Applications.

Data Center Building Block Solutions®

Supermicro DCBBS includes all critical computing, power, cooling infrastructure, software, and services. The modularized building block solution architecture—from system, to rack, to data center reduces cost and speeds up time-to-online.

Rack Scale Solutions

Accelerated time-to-delivery of plug and play racks with proven quality and reliability.

Unlocking Petascale Storage I/O in Multi-Tenant AI Environments with Nvidia Spectrum-X Ethernet Networking and IBM Storage Scale

In this solution brief, we will describe a high-performance storage cluster, purpose-built for the most demanding AI training and inference workloads running over an Ethernet network. The key components of the storage architecture include Supermicro’s Petascale server equipped with Micron E3.S NVMe, connected via NVIDIA Spectrum-X Ethernet.

SuperStorage® Scalable Storage Servers

Rack-scale storage systems for scale-out and scale-up software-defined storage applications including AI/ML Storage, CSP Storage and Enterprise Applications.

Data Center Building Block Solutions®

Supermicro DCBBS includes all critical computing, power, cooling infrastructure, software, and services. The modularized building block solution architecture—from system, to rack, to data center reduces cost and speeds up time-to-online.

Rack Scale Solutions

Accelerated time-to-delivery of plug and play racks with proven quality and reliability.

Unlocking Petascale Storage I/O in Multi-Tenant AI Environments with Nvidia Spectrum-X Ethernet Networking and IBM Storage Scale

In this solution brief, we will describe a high-performance storage cluster, purpose-built for the most demanding AI training and inference workloads running over an Ethernet network. The key components of the storage architecture include Supermicro’s Petascale server equipped with Micron E3.S NVMe, connected via NVIDIA Spectrum-X Ethernet.

Info

00

DAYS

:

00

HOURS

:

27

MINUTES

:

54

SECONDS

Architecting AI Inference and Data Management for Maximum Scale

August 19, 2026 | 5:00 PM - 5:45 PM UTC

Inference at scale requires optimization of compute, storage and networking performance. In this session, speakers discuss how IBM, Supermicro, and Kioxia can provide a highly scalable solution for AI inference. The session also explains why KV Cache and AI Data Platform (AIDP) are critical for improving inference response time and optimizing the design of an AI Factory. And the benefits that the combine solution brings for improving time-to-first-token responses and optimizing the data and compute design of AIDP on Supermicro all-flash storage systems.

William Li

GM, Solution Management Supermicro

Anders Graham

Sr. Director, SSD Marketing and Business Development KIOXIA

Ka Wai Leung

AI Solutions Product Management IBM