Desk

NVIDIA

NVIDIA hardware, software, and developer news.

AIAug 26, 2026NVIDIA Developer

How to Train a Cross-Embodiment Robot Navigation Policy with AI Agents

NVIDIA Developer published “How to Train a Cross-Embodiment Robot Navigation Policy with AI Agents” dated 2026-08-26. According to the NVIDIA Developer feed, navigation enables a robot to turn perception and motion into purposeful autonomy. The same item also notes that unlike locomotion, which produces stable movement, navigation must be used to... The same item also notes that navigation enables a robot to turn…

Read the brief

AIAug 26, 2026NVIDIA Developer

Experiment with Qwen3.8-Flash-Next on NVIDIA GB300 NVL72 for Agentic Coding

NVIDIA Developer published “Experiment with Qwen3.8-Flash-Next on NVIDIA GB300 NVL72 for Agentic Coding” dated 2026-08-26. According to the NVIDIA Developer feed, alibaba released the model weights for Qwen3.8-Flash-Next as a preview of the upcoming Qwen4 architecture for developers to experiment with and evaluate. The same item also notes that alibaba released the model weights for Qwen3.8-Flash-Next as a preview…

Read the brief

AIAug 25, 2026NVIDIA Developer

Restore LLM Inference Capacity in Seconds with Shadow Engine Recovery in NVIDIA Dynamo

NVIDIA Developer published “Restore LLM Inference Capacity in Seconds with Shadow Engine Recovery in NVIDIA Dynamo” dated 2026-08-25. According to the NVIDIA Developer feed, when an LLM engine process fails, the standard recovery path involves a cold restart. The same item also notes that this requires loading weights into HBM from storage, compiling kernels,... The same item also notes that when an LLM engine…

Read the brief

AIAug 25, 2026NVIDIA Blog

Leading Publishers Bring Blockbuster PC Games and Technology to NVIDIA RTX Spark

NVIDIA Blog published “Leading Publishers Bring Blockbuster PC Games and Technology to NVIDIA RTX Spark” dated 2026-08-25. According to the NVIDIA Blog feed, NVIDIA is bringing the next wave of RTX gaming to the Gamescom conference running this week in Cologne, Germany, with support for new games, anti-cheat technologies and increased visual quality. The same item also notes that electronic Arts, Embark and Ubisoft…

Read the brief

AIAug 25, 2026NVIDIA Developer

CUDA Python 1.0: Stable APIs, One Foundation, Full Platform Access

NVIDIA Developer published “CUDA Python 1.0: Stable APIs, One Foundation, Full Platform Access” dated 2026-08-25. According to the NVIDIA Developer feed, for years, a Python developer who needed a GPU had two realistic choices: Learn NVIDIA CUDA C++ well enough to write an extension, set up a build toolchain, and... The same item also notes that for years, a Python developer who needed a GPU had two realistic…

Read the brief

AIAug 24, 2026NVIDIA Developer

Giga-Scale AI and the Ethernet Evolution: How Spectrum-X Ethernet Rewrites the Rules

NVIDIA Developer published “Giga-Scale AI and the Ethernet Evolution: How Spectrum-X Ethernet Rewrites the Rules” dated 2026-08-24. According to the NVIDIA Developer feed, massive growth of generative AI has fundamentally altered data center design. The same item also notes that as distributed model training scales to span hundreds of thousands of GPUs,... The same item also notes that massive growth of generative…

Read the brief

AIAug 24, 2026NVIDIA Blog

How XPUs Meet a World-Class AI Factory

NVIDIA Blog published “How XPUs Meet a World-Class AI Factory” dated 2026-08-24. According to the NVIDIA Blog feed, to generate intelligence at scale, AI factories run continuously, and their economics are defined by delivered output: tokens per second, tokens per watt, cost per token, utilization and uptime. The same item also notes that that requires AI infrastructure designed and built as a full factory, not a…

Read the brief

AIAug 24, 2026NVIDIA Blog

With Groq 3 LPX in Full Production, NVIDIA Extends Vera Rubin Inference for Agents

NVIDIA Blog published “With Groq 3 LPX in Full Production, NVIDIA Extends Vera Rubin Inference for Agents” dated 2026-08-24. According to the NVIDIA Blog feed, next era of AI inference won’t be defined by a single breakthrough chip, network or system. The same item also notes that it’ll be defined by how every layer of the AI factory works together. The same item also notes that that’s why NVIDIA is extending Vera…

Read the brief

AIAug 24, 2026NVIDIA Blog

Up to 30x More Work Per Watt: NVIDIA Vera Rubin NVL72 Sets a New Efficiency Standard for AI Agents

NVIDIA Blog published “Up to 30x More Work Per Watt: NVIDIA Vera Rubin NVL72 Sets a New Efficiency Standard for AI Agents” dated 2026-08-24. According to the NVIDIA Blog feed, according to OpenRouter data, agentic AI workloads consume 15x more tokens than a simple chat request. The same item also notes that consider what happens when an AI agent researches a company for an investment decision. The same item also…

Read the brief

AIAug 24, 2026NVIDIA Developer

NVIDIA Vera Rubin and Blackwell Set a New Standard for Agentic AI Performance per Watt

NVIDIA Developer published “NVIDIA Vera Rubin and Blackwell Set a New Standard for Agentic AI Performance per Watt” dated 2026-08-24. According to the NVIDIA Developer feed, AI agents have expanded inference from single-turn interactions into multi-step workflows that reason, invoke tools, coordinate subagents, and carry growing... The same item also notes that AI agents have expanded inference from single-turn…

Read the brief

AIAug 24, 2026NVIDIA Developer

Maximizing AI Factory Performance per Watt with NVIDIA DSX MaxLPS

NVIDIA Developer published “Maximizing AI Factory Performance per Watt with NVIDIA DSX MaxLPS” dated 2026-08-24. According to the NVIDIA Developer feed, AI factories are power-constrained industrial systems. The same item also notes that question is no longer how many GPUs fit in a data center, but how much AI output each available... The same item also notes that AI factories are power-constrained industrial…

Read the brief

AIAug 24, 2026NVIDIA Developer

NVIDIA BlueField-4 Powers New Scale-In Network Infrastructure for Agentic AI Factories

NVIDIA Developer published “NVIDIA BlueField-4 Powers New Scale-In Network Infrastructure for Agentic AI Factories” dated 2026-08-24. According to the NVIDIA Developer feed, traditional cloud infrastructure was designed for predictable, general-purpose workloads and standard interfaces. The same item also notes that agentic AI factories connect diverse users,... The same item also notes that traditional cloud…

Read the brief