HPC just got hands-on at #SC26. Join us Monday, Nov. 16 for a hands-on Build-a-Claw featuring demos, experts, and more followed by a Special Address from NVIDIA’s @ia_buck covering the latest breakthroughs in #HPC. 🦞Build-a-Claw: 1–3:30 pm CT 🎙️Special Address with Ian Buck: 4–5 pm CT Spots are limited. Register now → nvda.ws/4k9k9Dt

Teams across Europe are adapting NVIDIA Earth-2 open models to answer weather and climate questions that matter to their work. @AXA is studying cyclone risk across more than 1,000 simulated seasons. @TotalEnergies is testing short-term solar forecasts at two solar farms. At the @OfficialUoM, researchers adapted Earth-2 CorrDiff to model U.K. air quality, training it on Isambard-AI and running it locally on DGX Spark. More from GTC Berlin in the blog: blogs.nvidia.com/blog/europe…

Space42 is estimating urban building heights from a single satellite radar image, even through clouds and in the dark. The team used NVIDIA Earth-2’s CorrDiff and PhysicsNeMo to generate height maps and flag areas where predictions are less reliable. Here’s how @space42ai built it: nvda.ws/4zqXLKl

Turn local weather data into real-time operational decisions With AI data assimilation tools in NVIDIA Earth-2, you can pipe proprietary and local sensor data directly into high-res forecasting models like CorrDiff, StormCast, and HealDA. No full model retraining required. Read the full Earth2Studio code walkthrough: nvda.ws/4cE3NOQ

Introducing CUDA Rust! CUDA Rust lets you write GPU kernels natively in Rust, not just launch them from it. Two paths: cuda-oxide for SIMT kernels compiled to PTX, and cutile-rs for Tile-based programming on stable Rust. Both can catch aliasing errors at compile time. Technical blog: nvda.ws/4hm1bHS

CUDA Toolkit 13.4 is now available. It adds Windows on Arm support, early developer support for NVIDIA Rubin, and MPS V3 controls for partitioning GPU compute and memory across workloads, plus new CUDA Python APIs and CCCL performance improvements. Here's all the technical details: nvda.ws/4A8VzbC

Join us for a three-part webinar series on how AI is being used to study proteins, forecast climate risk and simulate new materials. NVIDIA speakers will be joined by researchers from @emblebi, @OfficialUoM and @EPFL to share how teams are working with NVIDIA BioNeMo, Earth-2 and NVIDIA ALCHEMI. Sept 23 | Sept 30 | Oct 6 Available in multiple time zones. Register below.

NVIDIA cuPQC v0.6 is here! Introducing cuPQC-BigInt and cuPQC-NTT, GPU-accelerated math libraries for building cryptographic systems. Dive into big integer arithmetic (modular multiplication, inversion, exponentiation, and reduction) and number theoretic transforms for zero-knowledge proofs, fully homomorphic encryption, RSA, elliptic curve, and isogeny-based cryptography. Read the blog: nvidia.github.io/cuPQC/relea… Get started: developer.nvidia.com/cupqc

NVIDIA cuPhoton is now available on GitHub 🔭 Working with data from telescopes, X-ray sources and laser experiments often means spending months or years just getting the data ready to use. cuPhoton moves that pipeline onto the GPU to speed up that process, from ingest and cleaning to analysis, bringing it down to hours or minutes. Get started: github.com/nvidia/cuPhoton

NVIDIA nvmath-python v1.0 is now GA. Get the raw performance of CUDA-X math libraries (cuFFT, cuBLAS, cuSPARSE) directly inside your NumPy, CuPy, and PyTorch-based code. 🔹 Scale CPU ➡️ Single-GPU ➡️ Multi-node 🔹 Stateful APIs for reusable planning & autotuning 🔹 Fast JIT kernel fusion with numba-cuda Details: developer.nvidia.com/blog/ru…

Color codes have been out of reach for years, with no decoder fast or accurate enough to make them practical. That changes today. NVIDIA Ising Decoder ColorCode 1 Fast, the latest in the NVIDIA Ising open model family, gives QPU builders the flexibility to maintain data control and deploy anywhere with a 300x improvement in logical error rate and over 7x decoding speedup.

NVIDIA cuEST 0.2.0 is live. Our cuEST (CUDA-X Electronic Structure Theory) library now delivers faster, GPU-accelerated quantum chemistry calculations, along with many new features. Explore the latest capabilities and start accelerating atomic-scale simulations with cuEST 0.2.0, available today. 🔗 nvda.ws/44APhD4

Rare events are difficult to study precisely because conventional sampling rarely encounters them. NVIDIA researchers combine guided diffusion with probability correction to better estimate extreme-event likelihoods. Beyond climate, the approach could advance research in aerospace, robotics, finance, materials, molecular simulation, and infrastructure resilience. Explore the research: nvda.ws/4aNJL3u

nvidia-kaggle is now live and open-source on GitHub. We just dropped the plugin that gives AI agents (like Claude Code, Codex, or Agent SDK) the skills to run an entire Kaggle competition workflow from plain language. Featuring: 🤖 End-to-End Automation: Autonomously research competitions, mine top-team writeups, reproduce notebooks, and submit. 🔎 Anti-Hallucination Grounding: Built-in verification mechanisms (a reusable design pattern for any agentic workflow). 📈 Proven Agent Lift: Evaluated via our 3-tier NVBASE framework, showing massive performance gains with the skill turned on. 👉 Clone the repo and try it now: nvda.ws/4p8WYd6

Modern scientific instruments generate more data than traditional storage pipelines can keep up with. NVIDIA DAQIRI streams high-bandwidth sensor data directly to GPUs for real-time AI inference, filtering, and compression. It helps developers process data as it's created instead of storing everything first. Learn how facilities like @CERN are reducing storage bottlenecks. Read more: nvda.ws/4vXZB3m #ISC26

Are your sparse linear systems across computational science and engineering workloads still bottlenecking on the CPU? (Don't worry, we won't tell anyone.) 🤫 If you're an engineer building real-time simulations or chip design, it's time to let your GPU do the heavy lifting. cuDSS 0.8.0 is out. Here is what’s inside: ⚡ Speed: Faster solve for multiple right-hand sides (because nobody likes waiting). 🧠 Diet Mode: Lower device memory requirements and smoother multi-GPU scaling. 🔢 Extra Precision: New double-double numerics for when your math gets existential. 🛠️ Future-Proofing: Finalized API changes. From Pascal up to Grace Hopper, give your solver the GPU upgrade it deserves. 👉 Download cuDSS 0.8.0: nvda.ws/3SV9pgk

Science at the speed of light. 🧪 🌌 Unveiled at #ISC26, new CUDA-X software (cuPhoton, DAQIRI, and ALCHEMI) that turns days of research into real-time insights. From a 15,000x boost in telescope data analysis to accelerated materials discovery, we’re helping scientists unlock breakthroughs faster than ever. Read the full blog: nvda.ws/4w7DFTO

🎙️ From supercomputers to Silicon Valley, climate modeling is changing fast. Dr. @SciPritchard joined the @WeatherGeeks podcast to discuss Earth system modeling, AI, and how GPUs are helping researchers model Earth's climate at greater scale and resolution. A thoughtful conversation on where computing and climate science intersect. Worth a listen. art19.com/shows/weather-geek…

What happens when you let LLM agents write the code and NVIDIA GPUs do the heavy lifting? 🤖⚙️ In a Kaggle churn competition, it meant 150 stacked models, 850 runs, and a gold medal—powered by NVIDIA cuDF, NVIDIA cuML, XGBoost, and PyTorch. 🏅 Our latest blog breaks down the four-step playbook you can reuse for your own tabular ML. nvda.ws/41PDSxM

⚛️ Explore how AI physics can accelerate clean, modular nuclear reactor design. By leveraging NVIDIA CUDA-X libraries, PhysicsNeMo, and Omniverse libraries, see how nuclear developers address these challenges with GPU-accelerated digital twins. nvda.ws/4tmWYax

Build custom, GPU-native atomistic simulation workflows for chemistry and materials science with the new NVIDIA ALCHEMI Toolkit. 🧪🧬 See how @OrbitalHardware, MatGL and @matlantis_en have integrated their platforms with ALCHEMI and try it yourself with pip install nvalchemi-toolkit. ⚙️ Read more: nvda.ws/3OHp1lY

🌌 How to scale your HPC performance? In our upcoming developer livestream our CUDA team will share how NVSHMEM enables multiple GPUs to work in parallel on large-scale AI training, simulations, and rendering tasks. They'll walk through a live demo of NVSHMEM, dive deep on API calls to launch CUDA kernels across sets of GPUs, and end with a Q&A session. 📅 April 23, 1:00 PM - 1:30 PM CDT 📌 Register: nvda.ws/3QsameS Get your questions ready (and share in comments). We will see you there. 🙌

✨ Just published: technical guide for NVIDIA Ising 🥇 World’s first family of open AI models for building quantum processors AI-powered calibration + error correction workflows Delivers up to 2.5x faster decoding and 3x higher accuracy⚡ Built for fault-tolerant, hybrid quantum-classical systems Includes open models, weights, datasets, and workflow “recipes” for customization 📚 developer.nvidia.com/blog/nv…

Our new open-source AI model family will transform quantum computing by using agentic AI to solve it's most complex challenges, like real-time error correction. Nic Harrigan joins the NVIDIA AI Podcast to explain how NVIDIA Ising will help turn today's quantum hardware into tommorow's quantum-GPU supercomputers. 🌌 📺 Watch the full episode: piped.video/watch?v=OFEY5-52…

✨ How is AI reshaping the future of quantum computing? Don’t miss our Quantum Day, where top researchers, developers, and industry pioneers will share how they’re pushing the boundaries of quantum innovation across science and technology. We will also unveil new announcements on how we're accelerating quantum computing . . . 📅 April 14, 8 AM - 1:30 PM PT 📍 Online 💡 6 sessions with live Q&A 🔗 Spots are filling fast: nvda.ws/3PTJVi6

📜 And yes, there are even docs to get you started. You’re welcome. 🙌 github.com/NVIDIA/cuda-tile/…

💾 Now, developers with BASIC still burned into their brains can bring legacy applications to NVIDIA GPU-accelerated computing for the first time. Read the technical deep dive: developer.nvidia.com/blog/cu…

🌅 BASIC is BACK! In response to overwhelming demand from seasoned developers everywhere, we’re releasing cuTile BASIC for GPUs, bringing CUDA Tile programming to this long-overlooked language. 🧵 👇

Build your own accelerated, differentiable physics solvers in Python using NVIDIA Warp. ⚡ Our new blog uses a 2D Navier-Stokes example to show the fundamental patterns for writing GPU-native simulation kernels. See how these core concepts scale to production-ready workflows like Google DeepMind’s MJWarp and Autodesk Research XLB. Get started: nvda.ws/40NVjhJ

A bold bet on parallel computing paved the way for the AI revolution. We honor 20 years of #CUDA and thank the 6 million architects who turned a programming model into a global foundation for innovation. 💚 🔗 nvda.ws/4bQym3A

We are breaking the quantum chemistry bottleneck in semiconductor design with the launch of NVIDIA cuEST, a CUDA-X library that delivers up to a 55x performance boost for electronic-structure calculations. 🧬⚛️ Initial adopters including @Applied4Tech, @Samsung, TSMC, and @Synopsys are using these GPU-accelerated algorithms to simulate the atomic-scale physics of next-generation chips. 🔗 nvda.ws/3P4h2zr

We got you Bro. Shelly says "hello." @Baxate

🎉 "This is the 20th anniversary of CUDA. We have been working on this architecture for 20 years ... to now have built up hundreds of millions of GPUs and computing systems around the world that run CUDA."

The Genesis Mission is redefining what’s possible across HPC, quantum computing, and open AI models. Leaders from the U.S. Department of Energy (@ENERGY, @doescience) and NVIDIA will share how this private-public partnership is advancing the nation’s next generation of energy and scientific discovery. Don’t miss Science at the Speed of Light: The Genesis Mission Across DOE Labs at #NVIDIAGTC. 📆 Tuesday, March 17 | 11 - 11:40 a.m. PDT 🔗 nvidia.com/gtc/session-catal…

🌌 Two decades of debugging, optimizing, and rewriting the rules. #CUDA didn't just accelerate computing—it created a new way to build. 🙌 Join CUDA pioneers Stephen Jones, Paulius Micikevicius, Joe Stam, Kate Clark, and Wen-Mei Hwu at #NVIDIAGTC for an unfiltered look at how the platform you use every day was forged from code, curiosity, and caffeine. 🗓 Wed, Mar 18 | 3:00 p.m. PDT in person and livestreamed. 🔗 Add to schedule: nvidia.com/gtc/session-catal…

📢 cuTile.jl is here, bringing NVIDIA’s #CUDATile based programming to Julia. Unlock tensor cores and high-performance GPU kernels with idiomatic Julia syntax—no more manual thread management. ✅ Performance parity with cuTile Python ✅ Native Julia idioms (broadcasting, sum, sqrt) Write CUDA Tile kernels in Julia. 🔗 nvda.ws/4bnSGcm

🌍 Explore the future of weather prediction at #NVIDIAGTC. Learn how to predict weather change with AI in a hands-on lab on Thursday, March 19 at 1 p.m. Build local weather resilience using Earth-2, train generative AI models with PhysicsNeMo, and deploy high-resolution forecasting pipelines in real time. 👉 Add to your schedule: nvidia.com/gtc/session-catal…

🌌 Solving at scale with HPC × AI × Quantum #NVIDIAGTC brings developers and researchers together to share how accelerated architectures, parallel workflows, and new compute paradigms are pushing the limits of performance. Featured sessions: 🌍 [S82185] Earth System at 1 km Resolution 🏗️ [S82216] Architecting the AI Factory 🔭 [S81766] Accelerated Workflows at Scale ⚡ [S82236] TACC Horizon System Explore the full lineup of HPC and quantum sessions ➡️ nvidia.com/gtc/sessions/quan… ⏳ The conference is nearly sold out. Only day passes (Tues, Wed, Thurs) and exhibit passes remain. Register now.

Unlock the secrets of #CUDA with the experts who literally wrote the books. 🔓📗 Join NVIDIA’s top educators for a live session on GPU computing—from open-source C++/Python tutorials to a sneak peek at the new "Programming Massively Parallel Processors (5th Ed)". Featuring: ⭐ Izzat El Hajj (PMPP Author) ⭐ Tony Scudiero (CUDA Programming Guide Author) ⭐ Jonathan Bentz & Katrina Riehl (NVIDIA) 🔗 Add to your calendar. nvda.ws/4aqAptn

NVIDIA Earth-2 models are live.🌏 From predicting extreme weather to long-term climate simulations, get the resolution and speed you need to make a real-world impact. Get started: 🤗 Hugging Face: huggingface.co/collections/n… 💻 GitHub: github.com/NVIDIA/earth2stud…

🌍 Earth-2 Medium Range, powered by Atlas, enables high-accuracy weather prediction for medium-range forecasts across 70+ weather variables including temperature, pressure, wind and humidity. On standard benchmarks, it outperforms leading open models on the most common forecasting variables measured by the industry. #AMS2026 📗 Read the paper: research.nvidia.com/publicat…

🌎 Earth-2 Nowcasting, powered by StormScope, uses gen AI to make country-scale forecasts into kilometer‑resolution, 0-6-hour predictions of local storms and hazardous weather in minutes. It's the first to outperform traditional, physics-based weather-prediction models on short-term precipitation forecasting by simulating storm dynamics directly, harnessing AI to directly predict satellite and radar imagery. #AMS2026 📗 Read the paper: research.nvidia.com/publicat…

🌏 @tomorrowio_ is revolutionizing global weather data with real-time insights powered by NVIDIA and @Azure. Tomorrow.io can close global weather data gaps and improve storm prediction accuracy for a more weather-resilient world with our NVIDIA Earth-2, the CorrDiff model, and PhysicsNeMo. Watch the full video 🎥 piped.video/-tbRz33WANo

Earth-2 Global Data Assimilation, powered by HealDA, produces initial conditions for weather prediction — snapshots of the current atmosphere, including the temperature, wind speed, humidity and air pressure, at thousands of locations around the globe. 📝 Read the paper: research.nvidia.com/publicat… #AMS2026

AI weather and climate prediction is becoming more accessible than ever for enterprises, government agencies and scientists. Announcing new NVIDIA Earth-2 open-source weather models - available on @huggingface - enabling organizations to build sovereign forecasting systems. 🤗 huggingface.co/blog/nvidia/e… #AMS2026

🌦️ Run your own global weather forecast in just a couple of lines of code with NVIDIA Earth-2. This 5-minute, step-by-step tutorial shows you how. 👇 Or watch on YouTube: piped.video/watch?v=Sog6aCap… #AMS2026

🌍 Global weather models capture large-scale trends, but often miss local extremes like hurricanes and typhoons. This step-by-step technical guide shows how to use NVIDIA’s CorrDiff model to downscale coarse climate projections into high-resolution, bias-corrected fields. 📝 developer.nvidia.com/blog/ho… #AMS2026 @EnergySPG

Is your GPU code ready for what’s next? Join CUDA expert Stephen Jones for a live masterclass on unlocking the next generation of GPU performance with CUDA Tile, the most innovative addition to CUDA in years. Don't get left behind. Add to your calendar now. 🗓️ nvda.ws/49qIejr

Master the next generation of GPU programming with our new deep dive into NVIDIA #CUDA Tile. Learn how to implement high-performance matrix multiplication by shifting from thread-level to block-level programming. Read the full blog: nvda.ws/4sDEVNv