Models & Labs

NVIDIA Extends Vera Rubin for Agentic AI Inference

NVIDIA BlogAugust 24, 2026high confidence

Why it matters

→NVIDIA's Groq 3 LPX significantly boosts token generation speed, enhancing AI inference capabilities.
→The integration of Groq 3 LPX with Vera Rubin NVL72 optimizes AI infrastructure for large-scale applications.
→This development supports the shift towards more interactive and responsive AI systems.

NVIDIA Extends Vera Rubin for Agentic AI Inference — ©NVIDIA Blog

NVIDIA has announced the full production of its Groq 3 LPX, integrated into the Vera Rubin NVL72 platform, aimed at enhancing AI inference for agentic systems. The system achieves 3,400 output tokens per second, significantly outperforming competitors. This advancement is part of NVIDIA's strategy to optimize AI infrastructure for large-scale, interactive applications. The integration of Groq 3 LPX with Vera Rubin NVL72 is expected to boost performance and efficiency in AI factories, supporting the growing demands of agentic AI.

Read original

The story around this

Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.

NVIDIA Vera Rubin NVL72 Boosts AI Agent Efficiency

3 developments

Aug 24 · NVIDIA Blog
NVIDIA Vera Rubin NVL72 Boosts AI Agent Efficiency
Aug 24 · NVIDIA Blog
NVIDIA Extends Vera Rubin for Agentic AI Inference (This article)
Aug 29 · TechCrunch AI
Nvidia Expands AI Advantage Beyond GPUs↳ Nvidia shifts focus from GPUs to orchestrating AI systems and optimizing megascale data center infrastructure with Vera Rubin.

More in Models & Labs

Models & Labsmodels

llama.cpp b12029 adds CUDA 13 and Snapdragon support

This release quietly cements llama.cpp as the universal inference runtime by finally supporting NVIDIA's latest CUDA 13 stack alongside AMD's ROCm 10.0. The inclusion of native builds for Linux arm64 with Snapdragon chips, covering CPU, Adreno GPU, and Hexagon NPU, signals a serious push into mobile edge deployment. While Apple Silicon KleidiAI is disabled in this specific build, the broader hardware coverage means developers no longer need to compile from source for most modern accelerators. It’s less about new features and more about removing friction for anyone running local models on bleeding-edge or diverse hardware.

llama.cpp ReleasesNov 1, 2026

Models & Labsother

Apple Intelligence arrives in China via iOS 27.3

Apple is finally unlocking its AI suite for Chinese users with the iOS 27.3 beta, marking a significant regulatory milestone after months of approval delays. The rollout relies on Alibaba’s Qwen model rather than OpenAI, integrating features like notification summaries and visual intelligence directly into the OS. By sidestepping the new Siri in favor of established text and image tools, Apple is prioritizing immediate utility over the full generative experience. This move effectively brings Apple’s AI capabilities to a massive new market, albeit with localized constraints that distinguish it from the global release.

The Verge AIOct 30, 2026