NVIDIA Engineering Blog & Tech Articles
Computing platform company pioneering GPU technology, AI infrastructure, and accelerated computing solutions for developers and data scientists
4766 engineering articles, tutorials, and technical insights from NVIDIA's engineering team
Top Technologies
Latest Articles
Filter:
AI agents are becoming a standard part of development workflows, but general-purpose agents weren’t built with specialized infrastructure software such as…
Tanya Lenz
9 min read
--
Adding AI models to local applications requires a portable model format, a reliable runtime, and acceleration that works across target systems.
Luca Spindler
3 min read
Includes Code
--
Automatic speech recognition must handle how people actually speak, not only the languages and styles that dominate pretraining data.
Elizabeth Goodman
13 min read
Includes Code
--
Generative recommender (GR) systems are emerging as a powerful new approach for large-scale personalization. Instead of treating recommendation as a set of…
Tanya Lenz
10 min read
Includes Code
--
AI infrastructure engineers, storage developers, and cloud service providers need fast and secure access to high-capacity file and object storage to support AI…
Harish Arora
5 min read
--
An agent can finish a task and still take an inefficient path. A failed search can trigger another search. A truncated file read can lead to a command fetching…
Parallel work, model-family isolation, reversible changes, and GPU-backed validation shaped an open source project designed around coding agents NVIDIA TensorRT…
Tanya Lenz
10 min read
Includes Code
--
Vision-language models have made it possible to build visual AI agents that understand video at production scale. The harder problem is turning that capability…
To understand where agentic AI stands today, consider the last seismic shift in technology: the rise of the internet in the 90s. It was new and full of…
Tanya Lenz
7 min read
--
AI agents can be given a goal, write code, use tools, and keep working as new information becomes available. This opens the door to applications that…
Alex Watson
9 min read
Includes Code
--
Every unused watt is capacity left on the table. AI factories are typically provisioned for the unlikely moment when every GPU reaches peak power…
Sarah McKenney
8 min read
--
As language models grow, scaling dense architectures becomes increasingly expensive. In a dense transformer, every token passes through every layer…
Michelle Horton
6 min read
Includes Code
--
Radiology AI has made remarkable strides in detecting abnormalities across chest X-rays, pathology slides, and 2D scans. Yet one of the most clinically rich and…
Tanya Lenz
11 min read
Includes Code
--
Using NVIDIA Cluster Readiness Engine, teams can bring reliable GPU clusters to production with workload-driven validation.
Michelle Horton
10 min read
Includes Code
--
Kubernetes manages what runs on your nodes. Managing the nodes themselves is the challenge: kernel settings, system packages, storage layouts, security agents…
Michelle Horton
10 min read
Includes Code
--
An AI coding agent’s patch can pass tests yet fail when the server loads a real model and handles requests. Evaluating changes to inference-serving software…
Elizabeth Goodman
7 min read
Includes Code
--
As large language model (LLM) inference increasingly processes sensitive information and proprietary model context across personal, enterprise…
Tanya Lenz
6 min read
Includes Code
--
AI factories are power-limited systems that deliver maximum value when fully optimized. GPU workload placement is a key optimization.
Elizabeth Goodman
12 min read
Includes Code
--
NVIDIA DLSS 5 introduces DLSS 3D-Guided Neural Rendering and granular controls that help game developers add lifelike lighting and material detail while…
Elizabeth Goodman
6 min read
Includes Code
--
GPU acceleration can speed up compute-intensive robotics workloads, but a fast CUDA kernel alone does not guarantee a fast ROS 2 graph. As messages move between…
The compute and memory demands of generative AI increasingly exceed what a single GPU can provide. NVIDIA TensorRT multi-device inference is a new capability…
When you ship an AI agent, the key question is whether it can execute a chain of work across dozens of sequential tool calls against a live environment…
Elizabeth Goodman
10 min read
Includes Code
--
Weather-sensitive industries increasingly have access to observations that offer an earlier, more local view of changing conditions.
You’re deploying a model on a system. It starts up, prompts are getting responses. Now the hard question: Is this fast? Your instincts might lead you to send…
Elizabeth Goodman
10 min read
Includes Code
--
Agentic AI workflows can be used to prepare and validate digital twins for physical AI systems. Agents can inspect 3D scenes, author simulation-relevant data in…
AI agents are moving from cloud data centers to vehicles, robots, and other edge devices. Unlike a chatbot that answers a single prompt, an agent works through…
Elizabeth Goodman
7 min read
Includes Code
--
cuTile Rust () is a tile-based system for safe, idiomatic GPU kernel authoring in the Rust programming language. Extending the Rust ownership model to tile…
Tanya Lenz
18 min read
Includes Code
--
How can a 30B-parameter model activate only 3B parameters per token, and still use the capacity of the larger model? Nemotron 3.5…
Elizabeth Goodman
8 min read
--
How NVIDIA Groq 3 LPX Deterministic Execution Drives Power-Efficient High-Interactivity Inference on
Power is a defining constraint for AI factories. As AI workloads demand a full compute platform to serve them, each component of that platform must maximize…
Tanya Lenz
9 min read
--
For operators of large-scale AI factories, maximizing continuous output is essential for productivity. In massive-scale AI training, every GPU in the cluster…
Elizabeth Goodman
11 min read
--
Federated learning (FL) projects often begin with a straightforward setup: one server, a few clients, and one dataset at each site. As those projects grow…
Elizabeth Goodman
9 min read
Includes Code
--
Mixture of experts (MoE) has become one of the defining architectural trends in large-scale AI model training. DeepSeek, Qwen, and Mixtral are examples of MoE…
Tanya Lenz
12 min read
Includes Code
--
Deploying a large language model is only the first step toward production-ready serving. Production teams also need to serve as many concurrent users as…
Elizabeth Goodman
6 min read
Includes Code
--
Biomolecular structure prediction is now often run at proteome scale, where the goal is to move an entire worklist through the pipeline efficiently.
Elizabeth Goodman
10 min read
Includes Code
--
NVIDIA has one of the largest and most complex supply chains in the world, and its performance is measured from wafer-out to first token. The interval is in two…
Elizabeth Goodman
11 min read
--
Encode-prefill-decode (EPD) disaggregation is an inference optimization technique for multimodal models that separates the vision encoder stage from the prefill…
Tanya Lenz
13 min read
Includes Code
--
Every NVIDIA CUDA Toolkit release adds functionality and performance improvements that help developers get more from NVIDIA GPUs and the broader NVIDIA software…
In September 2026, NVIDIA announced it is leaning into native GPU programming in Rust. CUDA C++ and CUDA Python are mature, enterprise-grade toolchains…
Elizabeth Goodman
13 min read
Includes Code
--
Enterprise work spans messages, decisions, projects, and obligations that change over time. An AI agent that starts without this context must reconstruct it…
Tanya Lenz
6 min read
--
Running reasoning and agentic AI at the edge has been harder than it needs to be. Until recently, models capable of multi-step reasoning were too large to run…
Elizabeth Goodman
10 min read
Includes Code
--
Modern AI platforms are no longer a single application behind one login screen. A user may start in a central portal, open a governed dataset…
AI agents are learning to do more by working together. A lead agent can break a complex task into smaller jobs and assign those jobs to specialized subagents.
Tanya Lenz
10 min read
--
NVIDIA CUDA remains the foundation of GPU-accelerated computing, powering everything from scientific simulations to large-scale AI training. But writing correct…
Elizabeth Goodman
17 min read
Includes Code
--
This post is the third in a series on AI model co-design. It explores how to accelerate LLM inference while maintaining accuracy using speculative decoding and…
Tanya Lenz
14 min read
--
AI is changing the pace of cybersecurity. Agentic systems can coordinate work and pursue complex objectives over long horizons. Security teams are beginning to…
Michelle Horton
10 min read
--
The surge in AI adoption is transforming everything from chatbots to content generation. Still, a common pain point remains: How can organizations confidently…
Elizabeth Goodman
12 min read
Includes Code
--
Agentic AI is changing how research is done. AI scientists can read papers, propose hypotheses, call models, and determine which experiments to prioritize next.
Michelle Horton
11 min read
Includes Code
--
A perception stack is shaped by the vehicle that carries it. Move the same software to a new carline—for example, from an SUV to a sedan or another vehicle…
Michelle Horton
14 min read
Includes Code
--
Deploy an Open Model from Checkpoint to Inference in Two Commands with NVIDIA TensorRT Model Connect
Open AI models are evolving faster than ever, but bringing them into native applications can still require model-specific conversion, preprocessing…
Tanya Lenz
6 min read
Includes Code
--
AI factories must support increasingly large models and more complex reasoning workloads. To keep up with the insatiable compute demands of AI workloads…
Farshad Ghodsian
7 min read
--