AI Inference

Sep 09, 2026

When to Use Encode-Prefill-Decode Disaggregation to Accelerate Multimodal Model Serving

Encode-prefill-decode (EPD) disaggregation is an inference optimization technique for multimodal models that separates the vision encoder stage from the...
14 MIN READ
Sep 03, 2026

NVIDIA PAIR Virtual Inference Router Expands Available Compute on Your Local Network

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....
11 MIN READ
Sep 02, 2026

Co-Designing AI Models Using Speculative Decoding for Faster LLM Inference

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...
15 MIN READ
Sep 01, 2026

How to Size GPUs for AI Inference and TCO Without Overspending

The surge in AI adoption is transforming everything from chatbots to content generation. Still, a common pain point remains: How can organizations confidently...
13 MIN READ
Aug 28, 2026

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,...
6 MIN READ
Aug 24, 2026

How NVIDIA Groq 3 LPX Unlocks Ultrafast Interactivity at Long Context on NVIDIA Vera Rubin

NVIDIA Groq 3 LPX is the interactive AI inference accelerator for the NVIDIA Vera Rubin platform. At the core of the platform is NVIDIA Vera Rubin NVL72, the...
13 MIN READ
Aug 24, 2026

Maximizing AI Factory Performance per Watt with NVIDIA DSX MaxLPS

AI factories are power-constrained industrial systems. The question is no longer how many GPUs fit in a data center, but how much AI output each available...
13 MIN READ
Aug 20, 2026

How Generative Recommenders Are Redefining RecSys at Scale

Recommender systems (RecSys) are one of the most ubiquitous machine learning problems in the consumer internet industry yet notoriously difficult to train and...
11 MIN READ
Aug 11, 2026

NVIDIA JetPack 7.2.1 Adds Agentic Video Skills and T3000 Emulation

Video is a core data path across NVIDIA Jetson applications, from robotics and intelligent video analytics to industrial automation, healthcare, media...
7 MIN READ
Jul 31, 2026

Co-Designing AI Model Attention for Fast, Interactive Long-Context Inference

As agentic and long-context workloads become common, the context lengths increase and attention consumes a larger share of inference time (Figure 1). Because...
14 MIN READ
Jul 24, 2026

ModelExpress: Distributing Model Artifacts at the Speed of Light

Every byte moved has a cost. As model checkpoints grow to hundreds of gigabytes or even a terabyte, that cost adds up quickly. To make things even worse,...
12 MIN READ
Jul 21, 2026

Inside NVIDIA Rubin GPU Architecture: Powering the Era of Agentic AI

What began as discrete AI model training and human-facing chat interfaces has evolved into always-on AI factories dedicated to producing intelligence at scale....
15 MIN READ
Jul 14, 2026

Lessons From the Leaderboard: What 5,000+ Kagglers Taught Us About Improving AI Reasoning

The NVIDIA Nemotron Model Reasoning Challenge invited the Kaggle community to explore a focused question: What techniques can improve reasoning accuracy when...
11 MIN READ
Jul 10, 2026

AI Model Co-Design: Hardware-Friendly LLM Design

AI performance comes down to three dimensions:  Accuracy: How well the model reasons and produces outputs Throughput: How many tokens per second a...
17 MIN READ
Decorative image.
Jul 02, 2026

Hardware-Rooted AI Security That Won't Slow You Down

AI has transformed how organizations operate, driving unprecedented levels of productivity and innovation. However, AI adoption can be impeded by concerns...
6 MIN READ
Jun 23, 2026

Maximize AI Factory Energy Efficiency Through Full-Stack Inference and Training Optimizations

Power can account for 40% of the operating expenses (OpEx) to run an AI factory. Each watt can be spent on overhead, data ingestion, training, or generating...
10 MIN READ