Skip to Content
Dismiss
Innovazione
Una piattaforma creata per l'AI

Unificata, automatizzata e pronta a trasformare i dati in intelligence.

Scopri come
Dismiss
16-18 giugno, Las Vegas
Pure//Accelerate® 2026

Scopri come trarre il massimo dai tuoi dati. 

Registrati ora
Everpure + STN

Eliminating bottlenecks to unleash AI innovation

STN is expanding its industry-leading managed services portfolio with a new GPU-as-a-service offering powered by ultra-scalable FlashBlade//EXA storage and tailored for foundational AI model building.

Technicians managing server equipment in a data center Technicians managing server equipment in a data center
Actions
5 minuti tempo di lettura
Challenges
Building on its strong reputation for backup, disaster recovery, and infrastructure-as-a-service solutions, STN aimed to deliver a secure, enterprise-grade GPU-as-a-service offering optimized for the demanding requirements of foundation models.
Results
By building its new GPU One offering on FlashBlade//EXA, STN can manage massive AI data sets without metadata bottlenecks, allowing it to offer clients next-level performance for AI model development.
Boost
3X
in read throughout, from 35GB/s to 100GB/s
Increase
20%
in model training performance for one client
Increase
10%
in average performance for inference workloads
Impact
Zero
on latency when scaling to 192 nodes

Introduction

Headquartered in Pleasanton, California, STN provides a full spectrum of infrastructure and technology services for modern workloads. From high-quality managed services to hardware and software resale, STN offers tailored solutions that help customers unlock competitive advantage.

STN was founded with a singular vision: to be the partner that AI-first, security-driven organizations trust the most. To realize this ambition, the company is continually evolving and enhancing its solutions and services, backed by people deeply invested in customer success.

Sabur Mian, Chief Executive Officer and Founder of STN, explains: “From the start, we’ve focused relentlessly on what’s right for each individual customer. We’ve long worked with companies at the very cutting edge of emerging technologies such as AI, and we love to help our clients solve complex problems.”

"Everpure technology allows us to deliver data storage performance at unprecedented consistency for even the most demanding AI workloads."

Sabur Mian

Chief Executive Officer and Founder, STN

Staying ahead in a fast-moving sector

For more than eight years, STN has worked closely with Everpure™ to steadily expand its service offering. Starting with backup- and disaster-recovery-as-a-service offerings, the company now operates a comprehensive managed services portfolio.

“We started seeing more and more requests from AI start-ups to help run their GPU environments,” says Mian. “Creating a GPU-as-a-service offering was the natural next step on our journey.”

Exploring GPU-as-a-service opportunities

As it explored the GPU-as-a-service opportunity, STN identified a gap in the market for a specialized platform that could support even the most demanding AI factory workloads.

“If you talk to AI researchers working on foundation models, you’ll find that most of them spend a great deal of their time moving data from large object storage repositories to the platforms where the model training actually takes place,” explains Mian. “Model training relies on vast data sets with massive amounts of metadata. From a storage infrastructure perspective, one of the biggest challenges is serving up data fast enough to ensure that GPUs are utilized to the full.”

Teague Goddard, Director of Business Development and Partner Alliance at STN, comments: “Over the years, we’ve built up a strong reputation for secure, enterprise-grade services, and we are now HIPAA-certified, PCI-certified, and SOC2 and SOC3 compliant. We aim to bring that same rigor to the new GPU side of our business.”

Building on a comprehensive service portfolio

Drawing on a successful eight-year relationship with Everpure, STN chose to standardize its AI data layer on Everpure FlashBlade//S™ solutions, alongside deploying FlashBlade//EXA for its most demanding AI factory workloads.

Mian recalls: “Everpure cares about our clients as much as we do, and they’ve been with us since the very beginning of STN. The team went out of their way to set us up with our first FlashArray™ when we were a newly minted start-up with very limited capital to invest in infrastructure, and the relationship has stayed strong ever since. Taking care of clients is part of Everpure’s DNA, just like it is for us.”

Maximum scalability, minimum latency

By harnessing Everpure FlashBlade//EXA, STN gains a high‑density storage fabric designed for extreme throughput and low‑latency metadata operations—the perfect fit for the performance profile of large‑scale AI factories.

“With a traditional storage infrastructure, the main limiting factors are how close you can get your data to the GPUs—because you can’t beat PCI speeds—and how much of your data can live close to those AI workloads,” says Mian. “We had been experimenting with a distributed cache architecture based on JuiceFS [JFS] to improve cache performance and throughput. When we discovered that Everpure could deliver these capabilities natively via FlashBlade//EXA, we knew it would be ideal for our use case.”

“Data storage is the real differentiator for custom training, tuning, and performance. Everpure technology is playing a key role in setting our offerings apart from the competition.”

Teague Goddard

Director of Business Development and Partner Alliance, STN

Delivering a next-generation storage platform

Using an Everpure FlashBlade//S500 storage appliance, STN can deliver a scale‑out file and object tier for training data, checkpoints, features, logs, and model artifacts across many AI/ML and GPU-as-a-service workloads. Everpure FlashBlade//EXA adds multidimensional performance through massively parallel processing and scalable metadata IOPS to support STN’s extreme requirements.

In combination, the Everpure technologies deliver both scalable, low-latency metadata access and extremely high data throughput, helping to keep GPU utilization high at all times.

“Before we started with FlashBlade//EXA, the best read throughput we achieved with JFS was around 35GB/s—and that was on a highly optimized data set of small files,” says Mian. “Now, each node can use up to 800Gbps of front-end bandwidth and deliver as much as 100GB/s of throughput.”

Goddard adds: “Data storage is the real differentiator for custom training, tuning, and performance. Everpure technology is playing a key role in setting our offerings apart from the competition.”

Performance without limits

Through GPU One, STN is delivering game-changing performance for AI research. Engineered for continuous AI workload operation, GPU One provides industry-leading performance for model training, fine-tuning, inference, and high-throughput AI pipelines, powered by NVIDIA H100, H200, L40S, RTX PRO 6000, and B200 GPUs.

“Everpure technology allows us to deliver data storage performance at unprecedented consistency for even the most demanding AI workloads,” says Mian. “In a typical storage infrastructure, researchers might start training a model on four nodes and get good performance—but as soon as they start scaling up, that performance collapses. With FlashBlade//EXA, we’ve scaled up to 192 nodes so far, and we’ve yet to find the limit.”

He adds: “We recently had one of our FlashBlade//S500 clients test the new FlashBlade//EXA architecture. They saw an immediate 20% performance boost for their training workflows—and the only bottleneck they encountered was compute, not storage. We’re seeing those positive trends across the board, including a consistent 10% performance improvement for inference workloads.”

Looking ahead to a bright future

For STN, launching GPU One is just the latest phase in an ongoing evolution. The full-spectrum service provider anticipates a long and fruitful partnership with Everpure in the years to come.

Mian concludes: “We hope to provide a continuous feedback loop to Everpure so we can keep evolving our offerings together to deliver even more gains to our customers and improve our bottom line. At STN, we stay one step ahead of the marketplace, and Everpure is a key partner in helping us do that.”

About NVIDIA and Everpure

NVIDIA® and Everpure are collaborating to deliver an AI data platform for enterprises that accelerates and simplifies AI initiatives from development to delivery of near real-time business insights.
Learn More
More Stories Like This
“Our mission was to transform the way we were working directly with our consumers, but ultimately adapting to how the world was changing around e-commerce and the digital experience.”
How PENN Entertainment Eliminated Casino Floor Outages
ThinkOn scales global data services with Pure Storage
Il browser che stai usando non è più supportato.

I browser non aggiornati spesso comportano rischi per la sicurezza. Per offrirti la migliore esperienza possibile sul nostro sito, ti invitiamo ad aggiornare il browser alla versione più recente.

Personalize for Me
Steps Complete!
1
2
3
Personalize your Everpure experience
Select a challenge, or skip and build your own use case.
Strategie di virtualizzazione pronte per affrontare il futuro

Soluzioni di storage per tutte le tue esigenze

Consenti progetti di AI di qualunque dimensione

Storage a performance elevate per pipeline dei dati, formazione e inferenza

Proteggiti dalla perdita dei dati

Soluzioni di resilienza informatica che proteggono i tuoi dati

Riduci i costi delle operazioni su cloud

Storage efficiente dal punto di vista dei costi per Azure, AWS e private cloud

Accelera le performance di applicazioni e database

Storage a bassa latenza per le performance delle applicazioni

Riduci il consumo di energia e di ingombro del data center

Storage efficiente delle risorse per ottimizzare l'utilizzo dei data center

Confirm your outcome priorities
Your scenario prioritizes the selected outcomes. You can modify or choose next to confirm.
Primary
Reduce My Storage Costs
Lower hardware and operational spend.
Primary
Strengthen Cyber Resilience
Detect, protect against, and recover from ransomware.
Primary
Simplify Governance and Compliance
Easy-to-use policy rules, settings, and templates.
Primary
Deliver Workflow Automation
Eliminate error-prone manual tasks.
Primary
Use Less Power and Space
Smaller footprint, lower power consumption.
Primary
Boost Performance and Scale
Predictability and low latency at any size.
What’s your role and industry?
We've inferred your role based on your scenario. Modify or confirm and select your industry.
Select your industry
Financial services
Government
Healthcare
Education
Telecommunications
Automotive
Hyperscaler
Electronic design automation
Retail
Service provider
Transportation
Which team are you on?
Technical leadership team
Defines the strategy and the decision making process
Infrastructure and Ops team
Manages IT infrastructure operations and the technical evaluations
Business leadership team
Responsible for achieving business outcomes
Security team
Owns the policies for security, incident management, and recovery
Application team
Owns the business applications and application SLAs
Describe your ideal environment
Tell us about your infrastructure and workload needs. We chose a few based on your scenario.
Select your preferred deployment
Hosted
Dedicated off-prem
On-prem
Your data center + edge
Public cloud
Public cloud only
Hybrid
Mix of on-prem and cloud
Select the workloads you need
Databases
Oracle, SQL Server, SAP HANA, open-source

Key benefits:

  • Instant, space-efficient snapshots

  • Near-zero-RPO protection and rapid restore

  • Consistent, low-latency performance

 

AI/ML and analytics
Training, inference, data lakes, HPC

Key benefits:

  • Predictable throughput for faster training and ingest

  • One data layer for pipelines from ingest to serve

  • Optimized GPU utilization and scale
Data protection and recovery
Backups, disaster recovery, and ransomware-safe restore

Key benefits:

  • Immutable snapshots and isolated recovery points

  • Clean, rapid restore with SafeMode™

  • Detection and policy-driven response

 

Containers and Kubernetes
Kubernetes, containers, microservices

Key benefits:

  • Reliable, persistent volumes for stateful apps

  • Fast, space-efficient clones for CI/CD

  • Multi-cloud portability and consistent ops
Cloud
AWS, Azure

Key benefits:

  • Consistent data services across clouds

  • Simple mobility for apps and datasets

  • Flexible, pay-as-you-use economics

 

Virtualization
VMs, vSphere, VCF, vSAN replacement

Key benefits:

  • Higher VM density with predictable latency

  • Non-disruptive, always-on upgrades

  • Fast ransomware recovery with SafeMode™

 

Data storage
Block, file, and object

Key benefits:

  • Consolidate workloads on one platform

  • Unified services, policy, and governance

  • Eliminate silos and redundant copies

 

What other vendors are you considering or using?
Thinking...
Your personalized, guided path
Get started with resources based on your selections.