News
Deploy Long-Context Reasoning and Agentic Workflows with Mini Max M3 on NVIDIA Accelerated Infrastructure
20+ hour, 45+ min ago (421+ words) NVIDIA Developer Deploy Long-Context Reasoning and Agentic Workflows with Mini Max M3 on NVIDIA Accelerated Infrastructure - Mini Max M3, a 428 B parameter Mixture-of-Experts model with 1 M-token context and native multimodality, leverages NVIDIA Blackwell infrastructure to unify text, vision, and code tasks, supporting…...
Run Diffusion Gemma on NVIDIA for Developer-Ready, High-Throughput Text Generation
2+ day, 19+ hour ago (409+ words) | NVIDIA Technical Blog NVIDIA Developer Run Diffusion Gemma on NVIDIA for Developer-Ready, High-Throughput Text Generation - Diffusion Gemma, developed by Google Deep Mind and optimized for NVIDIA hardware, generates tokens in parallel using diffusion-based denoising, enabling much faster and more scalable…...
Model Quantization: Turn FP8 Checkpoints into High-Performance Inference Engines with NVIDIA Tensor RT
3+ day, 17+ hour ago (726+ words) Converting a quantized checkpoint into an NVIDIA Tensor RT engine bridges the gap between model optimization and production deployment, enabling faster inference, higher throughput, and more efficient GPU utilization at scale. This post picks up where we left off, walking…...
Train Models Faster with JAX and Max Text Using NVFP4 on NVIDIA Blackwell
4+ day, 17+ hour ago (751+ words) Pre-training frontier LLMs comes down to throughput. When training spans trillions of tokens across thousands of accelerators, every percentage point of step time can add up to days of training and substantial compute costs. Numerical precision is one of the…...
Dyno Sim: Simulating the Pareto Frontier
2+ week, 12+ hour ago (402+ words) Modern LLM serving is hard to tune because each deployment is a stack of interacting choices: model backend, tensor-parallel shape, prefill/decode split…...
How to Automate AI Model Documentation with the NVIDIA MCG Toolkit
2+ week, 21+ hour ago (243+ words) As AI models grow in complexity and regulatory scrutiny intensifies under frameworks including California’s AB-2013 and the EU AI Act, software teams face a…...
Synthesize Realistic 3 D Medical Images at Scale to Ship Pre'Trained Models
3+ week, 19+ hour ago (693+ words) High'quality 3 D medical imaging data is the foundation of modern radiology AI, but access to it is often constrained by data scarcity, privacy restrictions, and the high cost of expert annotation. As a result, training reliable 3 D medical imaging models…...
Automating and Optimizing Financial Signal Discovery with Multi-Agent Systems
3+ week, 1+ day ago (807+ words) In quantitative finance, researchers build algorithms to trade assets, derivatives, and other financial instruments. A key part of that work is finding signals: patterns in messy market data that may help predict future returns. These signals can come from price…...
Add a Specialized Deep Research Skill to Agent Harnesses
3+ week, 3+ day ago (852+ words) Teams building these agents must ground them in enterprise data, connecting data sources, routing queries, managing authentication, tuning prompts, evaluating outputs, and preserving source attribution. NVIDIA AI-Q packages this work into an open-source deep research blueprint that can be exposed…...
Mastering Agentic Techniques: AI Agent Evaluation
3+ week, 3+ day ago (542+ words) This post explains the key differences between model and agent evaluation and walks through five practical tips for evaluating AI agents as production systems. This evaluation approach focuses on trajectories, tools, and outcomes'not just model scores. While model and agent…...