Leveraging TMA Hopper primitives using Triton ⚡ Our latest blog provides a deeper dive into how TMA works for developers to understand the new async copy engine. 🔗 hubs.la/Q02Hsz4f0

🌟Unlock the Power of #QuantumComputing with the new CUDA-Q Academic Repository, a resource designed to transform theoretical knowledge into practical skills with a series of #Jupyter notebooks and supporting files now available absolutely free 🚀🔬 👉nvda.ws/4bZsrWK

👀 AI at Meta Llama 3.1 405B trained on 16K NVIDIA H100s - inference is #TensorRT #LLM optimized⚡ 🦙 400 tok/s - per node 🦙 37 tok/s - per user 🦙 1 node inference ➡️ nvda.ws/3LB1iyQ✨

🏆Our #datascience team secured first place Friday across all five tracks at the Amazon KDD Cup 2024. 👀Read the deep dive on their win, and their unique and innovative approach to solving these challenges. ➡️ blogs.nvidia.com/blog/nvidia-ai… The competition, themed “Multi-Task Online

Now available: powerful, visual, profiling tools for accelerated #Python built into #JupyterLab 🔥 Download #Nsight Tools JupyterLab Extension ➡️ nvda.ws/3SlsxB2 ✨

We are honored to share that our CEO, Jensen Huang, has been named a top 35 #HPC legend by @HPCWire for his visionary leadership and groundbreaking advancements in accelerated computing. nvda.ws/4fgsbFP

📣 New release: #NVIDIAModulus 24.07🌐New GNN enhancements & application samples for training with large meshes are here. Dive into advanced modeling with ease 🖥️✨ ➡️ nvda.ws/4fuvv0f #AI #MachineLearning

Just out: NVIDIA #HPC SDK v24.7 🎉 Now supporting Ubuntu 24.04, with new Fortran interfaces for CUDA Graphs & a major NVSHMEM API update. Note: Last release for RHEL 7. ➡️ nvda.ws/3Wx7zk8

📢 Announcing the #CUDA Toolkit, release 12.6 ✅Supports GB100 capabilities ✅New library enhancements to cuBLAS, cuFFT, cuSOLVER, cuSPARSE ✅Release of Nsight Compute 2024.3 📥 nvda.ws/3yiraMW

Project Ceiba, a collaboration between Amazon Web Services and NVIDIA, is set to build one of the largest #AI supercomputers in the world. #NVIDIADGX #Cloud Learn more about the project here: nvda.ws/4cgbmYT

Elevate your #quantum programming with NVIDIA #CUDAQ v0.8 🌌🖥️ Learn how new features make the development of performant hybrid-quantum classical applications even easier in our latest blog 👉nvda.ws/3X2RUKL #QuantumComputing #HPC #DataCenter

🌀 Hurricane help from #NVIDIAResearch: StormCast is a new #generativeAI model for emulating high-fidelity atmospheric dynamics. This model can enable reliable weather prediction at mesoscale which is critical for disaster planning and mitigation. ➡️ nvda.ws/3X9AsEx ⛈️

Discover how NVIDIA's #CUDA-Q platform helps scale #Quantum Clustering Algorithms ✨ Dive into the latest research by The University of Edinburgh, on reducing qubit counts and pushing the boundaries of quantum applications. ➡️ nvda.ws/3X01ZXx

From 400x faster simulations to 140x energy savings, see how NVIDIA’s CUDA GPU-accelerated computing is paving the way for sustainable computing. Read more: nvda.ws/3WTGqYI #CUDA #AI #SustainableComputing

🦙 Learn how we are optimizing llama.cpp #AI inference with #CUDA Graphs. Read more about it in our tech blog: ➡️ nvda.ws/3Z1FBzN #Nsight

📣 NERSC at Berkeley Lab is seeking proposals as part of its Quantum Computing Access Program. Those accepted will gain access to QuEra Computing Aquila neutral atom #quantumcomputer. Apply here ➡️nvda.ws/3Xnu9Nx 🌟

Exciting to see Colossus, the world’s largest GPU #supercomputer, come online in record time. Colossus is powered by NVIDIA's #acceleratedcomputing platform, delivering breakthrough performance with exceptional gains in #energyefficiency. Congratulations to the entire team!

🙌 Join us for a deep dive and live Q&A on the NVIDIA and LlamaIndex 🦙 #DevContest 🌟 📆 Sept 5 at 9 a.m. PT 📍 On Discord: nvda.ws/3MydIYA We'll cover all the details and resources you will need -- whether you're an experienced developer or new to NVIDIA and LlamaIndex.

🙌 NVIDIA experts share essential techniques to boost efficiency and optimize your GPU-accelerated apps with #CUDA. Dive into the basics of writing high-performance CUDA kernels, gain insights into GPU architecture, and enhance performance. ➡️ nvda.ws/47d8Hya 📖

Achieve up to 1.9x higher #Llama 3.1 performance with Medusa on #NVIDIAHGX H200 systems with NVLink Switch. Learn more now: nvda.ws/4dR24nM #DataCenter #GenerativeAI