Building AI Agents for AR Glasses and XR Devices with NVIDIA XR AI | NVIDIA Technical Blog
… Components and architecture of an intelligent XR Agent An intelligent XR Agent starts with live context from the user’s XR device. …
Search
Related topics:
Arch User Repository
Tracked topic
Arch User Repository
Nsight Aftermath SDK - Getting Started
Download Nsight Aftermath SDK System Requirements Operating Systems Windows 10 up to 21H2 Windows 11 up to 21H2 Ubuntu v22.04, v24.04 Redhat v8.8 Rocky Linux v9.4 Arch Linux GPU Architecture NVIDIA Pascal and newer GPU Driver 531.41 or newer Graphics APIs DirectX 12, DirectX Raytracing, Vulkan, Vul… …
How to Eliminate Pipeline Friction in AI Model Serving | NVIDIA Technical Blog
… NVIDIA maintains a repository of plugins , and community contributions expand it regularly. Best Practice 6: Design models with deployment in mind. When choosing architectures, evaluate the deployment cost of exotic operations early. …
Building Autonomous Vehicles That Reason with NVIDIA Alpamayo | NVIDIA Technical Blog
… From this starting point and the flexible plug-and-play architecture of AlpaSim, users can tweak contender behavior, modify camera parameters, and iterate on policy. …
How to Automate AI Model Documentation with the NVIDIA MCG Toolkit | NVIDIA Technical Blog
… Completion and accuracy vary by model and repository; repositories with richer READMEs and config files yield higher results. …
NVIDIA JetPack SDK Downloads and Notes Archive
… Jetson Linux 39.2 6/02/2026 Drivers Driver Package BSP Camera SIPL Sample Root Filesystem Jetson Linux API Reference Sources Driver Package BSP Sources Sample Root Filesystem Sources Yocto Recipes OE4T for Jetson Tools WebRTC Crosstool-NG Toolchain gcc Crosstool-NG Toolchain Sources CUDA Tools Brin…
Build Your Own Transaction Foundation Model for Financial Intelligence | NVIDIA Technical Blog
… To swap architectures, edit model. target and model.config. target in the YAML. …
Deploy Self-Evolving Agents for Faster, More Secure Research with a Hermes Agent and NVIDIA NemoClaw | NVIDIA Technical Blog
… Sam’s experience spans the full AI stack: he maintains core toolkit architecture, builds and evaluates specialized industry agents, and designs intuitive front-end interfaces that bring these powerful AI systems to life for end users. …
Advancing GPU Programming with the CUDA Tile IR Backend for OpenAI Triton | NVIDIA Technical Blog
… Prerequisites: CUDA version : CUDA 13.1 or higher GPU architecture : NVIDIA Blackwell GPUs for example, GeForce RTX 5080 ; previous GPU architectures will be enabled in upcoming CUDA releases Build from source When prerequisites are satisfied, clone and build the project from source: Clone the repo… …
Achieving Single-Digit Microsecond Latency Inference for Capital Markets | NVIDIA Technical Blog
… From within the top-level directory of the code, you can build the container and the benchmark, and prepare the models’ weights and inputs: make -C docker CUDA ARCHS=120-real LOCAL USER=1 release run CUDA ARCHS sets the target GPU architecture in cmake . …