Nvidia
@nvidia·2.2M subscribers·2.7K videos
NVIDIA Rubin CPX Accelerates Inference for Million‑Token Context AI
Posted
September 9, 2025
Views
57,643
Likes
442
Engagement
0.77%
September 9, 2025
57,643
442
0.77%
Every word spoken in this episode is indexed. Type any phrase to jump straight to the moment it was said.
Type any word or phrase that may have been spoken. Click a result to seek the player to that exact moment.
Try a name, a topic, or a quoted line
1:33Now PlayingSome of today’s most advanced AI workloads, like code and video generation, demand context processing at unprecedented scale, often exceeding one million tokens.
This is why NVIDIA is launching Rubin CPX: a GPU purpose‑built for the compute‑intensive context phase of inference.
Together with NVIDIA Dynamo orchestration and the Vera Rubin NVL144 CPX platform, Rubin CPX is ushering in a new era of end‑to‑end disaggregated inference architecture—setting benchmarks in performance, efficiency, and ROI for these high-value workloads.
Sentinel Indexing in Progress
Metadata and chapters are available. Claim extraction for this episode is pending.
All video content is delivered via YouTube embedded players in accordance with the YouTube Terms of Service. Sentinel provides research tools that promote discovery and accountability across political media.
