Train Small Orchestration Agents to Solve Big Problems
Using the right tool and model for a task is a challenging and ever-present engineering problem in agent design. At NVIDIA Research, we're making fast progress...
Build Efficient Financial Data Workflows with AI Model Distillation
Large language models (LLMs) in quantitative finance are increasingly being used for alpha generation, automated report analysis, and risk prediction. Yet...
How to Scale Data Generation for Physical AI with the NVIDIA Cosmos Cookbook
Building powerful physical AI models requires diverse, controllable, and physically-grounded data at scale. Collecting large-scale, diverse real-world datasets...
Making Robot Perception More Efficient on NVIDIA Jetson Thor
Building autonomous robots requires robust, low-latency visual perception for depth, obstacle recognition, localization, and navigation in dynamic environments....
As generative AI advances, organizations need AI agents that are accurate, reliable, and informed by data specific to their business. The NVIDIA AI-Q Research...
How to Get Started with Neural Shading for Your Game or Application
For the past 25 years, real-time rendering has been driven by continuous hardware improvements. The goal has always been to create the highest fidelity image...
Fusing Communication and Compute with New Device API and Copy Engine Collectives in NVIDIA NCCL 2.28
The latest release of the NVIDIA Collective Communications Library (NCCL) introduces a groundbreaking fusion of communication and computation for higher...
Building Scalable and Fault-Tolerant NCCL Applications
The NVIDIA Collective Communications Library (NCCL) provides communication APIs for low-latency and high-bandwidth collectives, enabling AI workloads to scale...
Training XGBoost Models with GPU-Accelerated Polars DataFrames
One of the many strengths of the PyData ecosystem is interoperability, which enables seamlessly moving data between libraries that specialize in exploratory...
How to Achieve 4x Faster Inference for Math Problem Solving
Large language models can solve challenging math problems. However, making them work efficiently at scale requires more than a strong checkpoint. You need the...
Streamline Complex AI Inference on Kubernetes with NVIDIA Grove
Over the past few years, AI inference has evolved from single-model, single-pod deployments into complex, multicomponent systems. A model deployment may now...
Enabling Multi-Node NVLink on Kubernetes for NVIDIA GB200 NVL72 and Beyond
The NVIDIA GB200 NVL72 pushes AI infrastructure to new limits, enabling breakthroughs in training large-language models and running scalable, low-latency...
Accelerating Large-Scale Mixture-of-Experts Training in PyTorch
Training massive mixture-of-experts (MoE) models has long been the domain of a few advanced users with deep infrastructure and distributed-systems expertise....
Scale Biology Transformer Models with PyTorch and NVIDIA BioNeMo Recipes
Training models with billions or trillions of parameters demands advanced parallel computing. Researchers must decide how to combine parallelism strategies,...
How to Predict Biomolecular Structures Using the OpenFold3 NIM
For decades, one of biology’s deepest mysteries was how a string of amino acids folds itself into the intricate architecture of life. Researchers built...
Make Sense of Video Analytics by Integrating NVIDIA AI Blueprints
Organizations are increasingly seeking ways to extract insights from video, audio, and other complex data sources. Retrieval-augmented generation (RAG) enables...
