Checked fact 43619 Nov 2026Money and compute

The release says the companies plan to develop disaggregated inference, including using NVIDIA GPUs for prefill and Rebellions NPUs for decode.

the company says This is the company's own statement about itself, not something we found out ourselves.

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

Their planned work includes using NVIDIA GPUs for prefill and Rebellions NPUs for decode

What the source said when we opened it, on 9 Nov 2026.

The source

NVIDIA, Rebellions and SK Telecom Announce Collaboration to Advance Sovereign AI Infrastructure With NVIDIA NVLink Fusion
NVIDIA Newsroom · 2026-11-08

Open the source archived copy

Checked

Checked by the notis newsroom on 9 Nov 2026, against the source above.

In the story

Nvidia, Rebellions and SK Telecom plan a Korean inference system, with R200 systems expected in 2028. 9 Nov 2026

Cite this fact

Short permanent address

In a sentence

The company says: “The release says the companies plan to develop disaggregated inference, including using NVIDIA GPUs for prefill and Rebellions NPUs for decode.” ai notis, checked 9 Nov 2026. Source: NVIDIA, Rebellions and SK Telecom Announce Collaboration to Advance Sovereign AI Infrastructure With NVIDIA NVLink Fusion (NVIDIA Newsroom). https://ainotis.com/c/4361

As a reference (APA style)

ai notis. (2026, November 9). The company says: The release says the companies plan to develop disaggregated inference, including using NVIDIA GPUs for prefill and Rebellions NPUs for decode [Checked claim 4361]. ai notis. https://ainotis.com/c/4361

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