ToolClaude Code1 recent entries23 Sept 2026How SWE-Serve Exposes the Gap Between Local Tests and Live ServingSWE‑Serve evaluates AI coding agents on 53 inference‑engineering tasks derived from SGLang pull requests across six functional domains. Among 19 tasks that launch a live server, patches that pass loca
ToolLangChain3 recent entries20 May 2026Add a Specialized Deep Research Skill to Agent HarnessesThis article covers the NVIDIA AI-Q Blueprint for building specialized deep research agents that empower AI systems to gather context, synthesize information, and support complex decision-making acros
ToolOllama1 recent entries3 Sept 2026NVIDIA PAIR Virtual Inference Router Expands Available Compute on Your Local NetworkNVIDIA’s PAIR Virtual Inference Router distributes AI inference requests across multiple local machines—supporting Ollama and LM Studio without any agent or harness changes—to mitigate multi‑agent bot
ToolVercel AI2 recent entries3 Sept 2026How to Carry User Identity Across Federated Kubernetes and AI PlatformsA centralized identity gateway pattern decouples session ownership from request enforcement across federated Kubernetes clusters, letting regional gateways validate user identities via a shared Redis‑→28 Sept 2026Add Runtime Controls to AI Agents with NVIDIA OpenShellNVIDIA OpenShell 0.1.0 is an open‑source runtime that enforces which systems and data an AI agent may access without requiring changes to the agent itself. Its components—Gateway, Supervisor, Sandbox,
ToolHugging Face7 recent entries19 Aug 2026Post-Train NVIDIA Cosmos 3 Edge for On-Device Robot ControlNVIDIA’s Cosmos 3 Edge is a 4‑billion‑parameter omni‑model (with a 2‑billion‑parameter Nemotron reasoner) that can run on an NVIDIA Jetson Thor, providing on‑device policy inference for robot manipula→28 Aug 2026Deploy an Open Model from Checkpoint to Inference in Two Commands with NVIDIA TensorRT Model ConnectNVIDIA TensorRT Model Connect delivers a set of reference implementations for deploying open‑source models from Hugging Face checkpoints to native C++ inference in two steps: a Python CLI builds a dep→31 Aug 2026Scale AV Perception Across Vehicle Platforms with NVIDIA Omniverse NuRecNVIDIA Omniverse NuRec reconstructs real‑world driving scenes through 3D Gaussian splatting to produce the Physical AI NuRec Dataset—over 1,500 neural‑reconstructed videos (~20 s each) captured from s→8 Sept 2026Introducing CUDA Rust: Two Tracks for Writing GPU KernelsNVIDIA introduced two Rust projects for GPU development in September 2026: `cuda‑oxide`, a nightly‑only backend that compiles SIMT‑style kernels to PTX via LLVM and uses DisjointSlice and launch contr→24 Sept 2026Efficient MoE Training for Biological Foundation ModelsMixture‑of‑Experts (MoE) models scale capacity more efficiently than dense transformers by activating only a subset of expert subnetworks per token. NVIDIA’s Transformer Engine optimizes MoE training →1 Oct 2026Fine-Tuning NVIDIA Nemotron for Saudi Arabic Dialects, with a Path to Other LanguagesNVIDIA Nemotron 3.5 ASR was fine‑tuned on 133.7 h of Saudi Najdi and Hijazi speech using weighted replay with FLEURS data, duration bucketing, and selective encoder unfreezing; this reduced the target→1 Oct 2026Build Local AI Apps with C++ and NVIDIA TensorRT RTX SamplesThe Nvidia Deploy repository provides open‑source C++ samples that pair ONNX Runtime with the TensorRT RTX execution provider to accelerate local inference on Windows and Linux. It separates model exp