> Markdown version of [/events/world-congress-2025/sessions/586-your-next-ai-needs](https://www.wearedevelopers.com/events/world-congress-2025/sessions/586-your-next-ai-needs). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Your Next AI Needs 10,000 GPUs. Now What?


- **Date:** Thursday, Jul 10, 2025
- **Time:** 13:30–14:00 (30 min)
- **Room:** Stage 5
- **Event:** World Congress 2025

## Recording

[Watch recording](https://www.wearedevelopers.com/videos/1590-your-next-ai-needs-10-000-gpus-now-what)

## Description

As Large Language Models become foundational to modern applications, the complexity of securing and managing the right GPU infrastructure is a critical bottleneck. This session demystifies GPU consumption at scale, from single-GPU setups to vast, multi-node clusters. We will then introduce NVIDIA DGX Cloud Lepton, a revolutionary AI platform and compute marketplace. Discover how Lepton connects developers to a global network of cloud partners, unlocking access to tens of thousands of GPUs to build the next generation of AI.

Key Takeaways:

- GPU and multi-node system architectures for AI.
- Navigating abstraction layers: Bare Metal, VMs, and Kubernetes.
- Unifying access with the DGX Cloud Lepton compute marketplace.
- Achieving location and vendor-agnostic AI deployment.

## Speakers

### [Anshul Jindal](https://www.wearedevelopers.com/@anshul-jindal)

Sr. Solution Architect at NVIDIA
### [Martin Piercy](https://www.wearedevelopers.com/@martin-piercy)

Sr Solutions Architect, Nvidia


## Related talks at this congress

- [NVIDIA Expert Session: Your AI, Everywhere: Unifying Infrastructure for Unbounded Innovation](https://www.wearedevelopers.com/events/world-congress-2025/sessions/839-nvidia-expert) — Anshul Jindal, Martin Piercy
- [A Deep Dive on How To Leverage the NVIDIA GB200 for Ultra-Fast Training and Inference on Kubernetes](https://www.wearedevelopers.com/events/world-congress-2025/sessions/538-a-deep-dive-on-how) — Kevin Klues
- [NVIDIA Expert Session: Optimized Deployment of Large Language Models](https://www.wearedevelopers.com/events/world-congress-2025/sessions/491-nvidia-expert) — Anshul Jindal, Kevin Klues, Martin Piercy
- [Unveiling the Magic: Scaling Large Language Models to Serve Millions](https://www.wearedevelopers.com/events/world-congress-2025/sessions/907-unveiling-the-magic) — Patrick Koss