Checked fact 231322 Oct 2026Money and compute

Nvidia's blog says that in tests on GB300 NVL72 systems Nscale demonstrated that Nvidia DSX MaxLPS enabled 37% more GPUs and nearly 50% higher aggregate inference throughput within the same provisioned power budget; a vendor-reported result, not independently measured.

Toned down to what the source says

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

In tests using NVIDIA GB300 NVL72 systems, Nscale demonstrated that NVIDIA DSX MaxLPS enabled 37% more GPUs

What the source said when we opened it, on 22 Oct 2026.

The source

NVIDIA Cloud Partners Scale Across Europe
NVIDIA · 2026-10-21

Open the source archived copy

Checked

Checked by the notis newsroom on 22 Oct 2026, against the source above.

In the story

Nvidia announced an OpenShell reference architecture for AI agents at GTC Berlin and named European cloud partners. 22 Oct 2026

Cite this fact

Short permanent address

In a sentence

“Nvidia's blog says that in tests on GB300 NVL72 systems Nscale demonstrated that Nvidia DSX MaxLPS enabled 37% more GPUs and nearly 50% higher aggregate inference throughput within the same provisioned power budget; a vendor-reported result, not independently measured.” ai notis, checked 22 Oct 2026. Source: NVIDIA Cloud Partners Scale Across Europe (NVIDIA). https://ainotis.com/c/2313

As a reference (APA style)

ai notis. (2026, October 22). Nvidia's blog says that in tests on GB300 NVL72 systems Nscale demonstrated that Nvidia DSX MaxLPS enabled 37% more GPUs and nearly 50% higher aggregate inference throughput within the same provisioned power budget; a vendor-reported result, not independently measured [Checked claim 2313]. ai notis. https://ainotis.com/c/2313

Anyone may quote this address. It does not change; if we correct the story, this page says so.