NVIDIA Developer

The Secret to Cheaper LLM Inference: NVFP4

Short | 1 months ago

What Is NVFP4? Faster LLM Inference Without Losing Quality

Guide | 1 months ago

Learn what NVFP4 is, why it helps you run bigger LLMs on less GPU memory without a big quality hit, and how to create an NVFP4‑quantized Nemotron 3 Ultra checkpoint using NVIDIA Model Optimizer. For more details, see these blogs on Nemotron 3 Ultra NVFP4 qu...

How to Customize NVIDIA Nemotron 3 Nano With RLVR in Prime Intellect Lab

Guide | 1 months ago

Customize NVIDIA Nemotron 3 Nano with reinforcement learning with verifiable rewards (RLVR) using Prime Intellect Lab. This tutorial walks through a complete customization workflow: baseline Nemotron 3 Nano in the math-python environment, train a LoRA adapt...

Build and Optimize Robotics and Edge AI with the New Jetson Thor T2000 and T3000

Guide | 1 months ago

As robotics and edge AI move into real-world deployment, developers need compact, power-efficient computing that can run foundation models and advanced AI workloads at the edge. Join NVIDIA product managers and engineers for a technical overview of the new ...

Tune the Harness, Before Tuning the Model with LangChain | Nemotron Labs

Guide | 1 months ago

When an agent fails, the instinct is to fine-tune the model. Often the actual bug is in the harness around it — the prompts, tool descriptions, and middleware the model never sees during training. This live tutorial shows how to fix that instead: run an eva...

Code with Me: Run Your Polars Code on the GPU

Guide | 1 months ago

Polars is one of the fastest-growing DataFrame libraries in the Python ecosystem, and now you can run the same Polars code on the GPU with cudf-polars. In this "Code With Me" session, Brian Tepera (PM for NVIDIA), William Hill (TME for NVIDIA), and Robin va...

Meet Jetson Thor: the perfect device to run Cosmos.

Short | 1 months ago

Build Multi-Camera 3D Tracking Applications with NVIDIA DeepStream 9.1 Skills

Stream | 1 months ago

NVIDIA DeepStream is an open-source streaming analytics tool and skills for real-time, AI-powered multi-sensor processing across video, audio, and images. DeepStream 9.1 accelerates vision AI development with agentic skills that help developers move from na...

Stylized Stock Returns w/ KDE

Short | 1 months ago

A stylized fact of returns → Returns are not normal. KDE → bell curve, but KDE is slow to compute on CPU, fast on GPU. Notebook → github.com/will-hill/GPU-Quant-Finance

Post-Train NVIDIA Cosmos 3 In a Day with NVIDIA TAO Agent Skills | Cosmos Labs

Guide | 1 months ago

Last-mile accuracy remains a challenge in physical AI, with training data bottlenecks and slow post-training iteration cycles slowing teams down. NVIDIA Cosmos 3 is the open frontier omni-model for physical AI — and now with NVIDIA TAO agentic skills, you c...

DGX Spark Live: Autonomous AI Agent Migration

Stream | 2 months ago

Join Arm, the world leader in energy-efficient AI compute, for a local agent demo on the HP ZGX Nano AI Station, powered by DGX Spark. This live demo will showcase an NVIDIA NemoClaw agent running Qwen3-Coder entirely on-device. Attendees will watch the age...

How to Run RL Autoresearch with Agent Skills | Nemotron Labs

Guide | 2 months ago

Coding agents can now run RL experiments on open models like Nemotron end to end — handling setup, running multi-hour autoresearch campaigns, and dramatically improving model accuracy on tasks you define. NVIDIA verified agent skills make this practical on ...