Search posts, papers, and topics
12 posts · blogs.nvidia.com
NVIDIA introduced DSX Ready, a qualification program for power and cooling products that meet its AI‑factory reference design requirements. The first categories—battery energy storage systems and cooling distribution units—now have qualified partners such as Hitachi Energy, LG, Tesla, LiquidStack, and Vertiv.
NVIDIA’s Halos platform is a full‑stack safety system for physical AI (autonomous vehicles and industrial robots). It bundles safety‑engineered hardware (DRIVE AGX Thor, IGX Thor), an ASIL‑D certified OS (Halos OS), middleware for isolation and monitoring, AI models for explainability (Alpamayo), and simulation/validation tools (Isaac Lab, Omniverse). The blog argues that scaling physical AI requ…
NVIDIA highlights Egypt’s rapidly expanding AI ecosystem, noting a ten‑fold rise in Deep Learning Institute learners, a $400 M data‑center project, and new AI factories delivering local GPU compute. The piece lists several Inception startups and broader African infrastructure plans, but offers no technical details.
Nvidia frames AI security as an engineering discipline, outlining required controls across the AI agent stack (model, harness, runtime) and advocating for enforceable boundaries, traceable identities, and evidence‑based testing. It highlights OpenShell as a sandboxed runtime, the Open Secure AI Alliance, and several vendor tools for testing and red‑team exercises.
Nvidia’s blog spotlights five companies that are using Nvidia AI platforms to accelerate clean‑energy projects—from grid interconnection and nuclear plant operations to off‑grid AI data‑center power, advanced reactors, and fusion tokamaks. The article is a marketing summary and provides few technical details.
Nvidia announced that the new creature‑catching game Aniimo and several other titles are now available on GeForce NOW, with features like path‑tracing for 007 First Light and RTX 5080‑class streaming for premium members. The update also lists 11 new games joining the service and notes a day‑pass that can be applied toward a monthly membership.
NVIDIA’s Vera Rubin NVL72 AI inference system shows up to 3.7× higher throughput than the prior GB300 NVL72 on MLPerf v6.1 benchmarks (Qwen3‑VL, DeepSeek‑R1), achieves 99% scaling efficiency across 288 GPUs, and benefits from software optimizations (NVFP4 precision, kernel fusion, disaggregated serving). The post is a product announcement with concrete benchmark numbers but limited technical dept…
Emerald AI, Google, and NVIDIA launched the AI Energy Management Alliance (AEMA) to advance data centers that can dynamically manage electricity use based on grid conditions. This aims to unlock faster, larger connections for AI infrastructure while supporting energy systems and communities.
University of Manchester used NVIDIA Earth‑2 CorrDiff and StormCast generative models to downscale UK‑wide air‑pollution simulations. Training on the Isambard‑AI supercomputer (5,448 GH200 chips, 21 EFLOPS) took two days on an eight‑GPU node, producing a 2‑3 km resolution model. Inference runs on a desktop‑class DGX Spark, enabling rapid scenario forecasting and potential real‑time health alerts.…
Nvidia’s Jensen Huang announced Salesforce’s Koa, a CRM‑reasoning LLM built by fine‑tuning Nvidia Nemotron 3 Super on a synthetic, three‑decade‑spanning dataset. Koa uses supervised fine‑tuning plus RL (NeMo RL, Gym, AutoModel), covers 14+ industries, and claims 3× fewer errors on Salesforce’s CRM‑Bench versus leading models. It’s already in internal Slack agents and slated for limited customer p…
NVIDIA’s DSX platform lets AI data‑centers shift workloads in response to grid signals, squeezing ~24% more token throughput (4 M→5 M tps) and ~23% better performance‑per‑watt on a fixed megawatt budget. The first production demo used Emerald AI’s Conductor to drop a 4 MW load to 3 MW in under a minute without interrupting high‑priority jobs. DSX MaxLPS reallocates headroom across HGX B200 server…
NVIDIA showcased new power‑aware AI‑factory features at the AI Infra Summit. DSX MaxLPS and Flex improve token‑per‑watt efficiency by up to 40%, while the Vera Rubin NVL72 platform delivers up to 30× higher throughput per megawatt on agentic workloads.
