How NVIDIA Uses V

Teams customize their models to hit their targets for latency, speed, memory, and compute. With the open NVIDIA Nemotron family of models…

As agentic and long-context workloads become common, the context lengths increase and attention consumes a larger share of inference time (Figure 1).

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.

Developers building 3D, design, simulation, robotics, and industrial digital twin applications need ways to bring physical AI capabilities into the tools and…

What if autonomous coding AI agents could push your vision reasoning models above 90% accuracy with almost no manual effort? When adapting vision reasoning…

AI performance comes down to three dimensions: Deployments must balance all three: High accuracy is wasted if responses are slow, and raw throughput means…

Generative AI workloads are rapidly outgrowing the memory and compute budget of single GPUs. For inference developers building media generation pipelines…

Physical AI—robots working autonomously alongside people in factories, warehouses, hospitals, and homes—is arriving faster than most expected.

Mixture-of-experts (MoE) models have quickly become a foundational component of modern, large-scale AI systems. They are widely adopted because they enable…

Quick glossary for readers new to VLA/WAM terminology VLA Vision-Language-Action model: a robot policy that starts from a pretrained VLM backbone and adapts it…

NVIDIA CompileIQ tackles one of the hardest problems in performance engineering: finding the compiler options that unlock the best performance for a specific…

This post is the second of a three-part series. See also Model Quantization: Concepts, Methods, and Why It Matters and Model Quantization: Turn FP8 Checkpoints…

Creative and visualization teams today produce more assets, in more formats, with leaner teams. Generative AI can accelerate that work – compressing tasks that…

The development of socially acceptable nuclear reactors requires that they are safe, clean, efficient, economical, and sustainable.

In vision AI systems, model throughput continues to improve. The surrounding pipeline stages must keep pace, including decode, preprocessing, and GPU scheduling.

In the rapidly evolving landscape of large language model (LLM) development, NVIDIA Megatron Core has emerged as the foundational framework for training massive…

In this post, we dive into one of the most critical workloads in modern AI: Flash Attention, where you’ll learn: Environment requirements: See the quickstart…

The article discusses NVIDIA TensorRT LLM AutoDeploy, a beta feature that automates the inference optimization process for large language models (LLMs).

This article introduces Dynamic Context Parallelism (Dynamic-CP), a scheduling approach in NVIDIA Megatron Core designed to optimize training for variable-length sequences in large-scale models.

The article discusses the advancements in AI technologies and infrastructure that shaped the year 2025, focusing on NVIDIA's innovations in AI factories, physical AI, and model optimization.

The article discusses the Skip Softmax technique, a method for accelerating long-context inference in large language models (LLMs) using NVIDIA TensorRT-LLM.

The article discusses NVFP4 KV cache quantization, a new key-value format that significantly enhances inference performance on NVIDIA Blackwell GPUs.

The article discusses neural shading as a transformative approach to real-time rendering, integrating trainable models into graphics pipelines to enhance visual fidelity and performance.

The NVIDIA Blackwell architecture has achieved the fastest training times across all MLPerf Training v5. 1 benchmarks, showcasing significant advancements in AI training performance.

The article discusses the enhancements in cuBLAS with the introduction of floating-point emulation for Tensor Core performance, particularly focusing on double-precision (FP64) matrix multiplicatio...

This article discusses the optimization of vision AI workloads using NVIDIA's CUDA-accelerated implementation of SMPTE VC-6, a codec designed for efficient interaction with modern compute architect...

The article discusses the optimization of large language models (LLMs) through post-training quantization (PTQ), emphasizing its benefits in enhancing inference performance while maintaining accura...

The article discusses CUTLASS, a library developed by NVIDIA for handling multidimensional data through tensors and spatial microkernels. It highlights the advancements in CUTLASS 3.

The article discusses the process of porting CPU applications to NVIDIA GPUs to enhance performance, particularly in the context of Électricité de France's (EDF) fluid dynamics simulations using th...

The article discusses the advancements in large language models (LLMs) focusing on the importance of extended context lengths for processing and generating text.

NVIDIA has set a new world record for large language model inference speed, achieving over 1,000 tokens per second per user with the 400-billion-parameter Llama 4 Maverick model on a single NVIDIA ...

NVIDIA is pioneering the shift to 800 VDC architecture to meet the growing power demands of AI factories, moving beyond traditional 54 V systems.

NVIDIA has announced the general availability of Secure AI, focusing on protecting data and code during AI training and inference, particularly for large language models (LLMs).

The article discusses the Marco framework, a configurable graph-based task-solving and multi-AI agent system designed to streamline chip design processes.

This article discusses how to build a movie recommendation system using NetworkX, Jaccard Similarity, and NVIDIA cuGraph to enhance performance.

Researchers from Weill Cornell Medicine have developed the Blastocyst Evaluation Learning Algorithm (BELA), an AI-powered model that enhances embryo selection in in vitro fertilization (IVF) by eva...

The article discusses the development of a 172 billion parameter large language model (LLM) with strong Japanese capabilities using NVIDIA Megatron-LM.

The article discusses the integration of the AWS Energy HPC Orchestrator with NVIDIA Energy Samples to enhance high-performance computing (HPC) in the energy sector.

The article discusses the integration of NVIDIA's NVENC technology with V-Nova's MPEG-5 Part 2 Low-Complexity Enhancement Video Coding (LCEVC) standard to create customizable GPU-accelerated video ...

The article discusses NVIDIA's advancements in audio generative AI with the introduction of BigVGAN v2, a universal neural vocoder that synthesizes audio waveforms with state-of-the-art quality and...

NVIDIA has fully transitioned to open-source GPU kernel modules with the upcoming R560 driver release, enhancing support for various GPU architectures while providing substantial new capabilities.

The article discusses the integration of advanced AI and Retrieval-Augmented Generation (RAG) techniques in high-performance computing (HPC) code development.

This article discusses the advancements in graph analytics through a next-generation architecture utilizing NVIDIA cuGraph acceleration.

NVIDIA has announced the general availability of its Confidential Computing solution on NVIDIA H100 Tensor Core GPUs, which provides enhanced security for data in use, particularly for AI applicati...

The article discusses the application of Mixture of Experts (MoE) in large language model (LLM) architectures, highlighting its benefits in terms of model capacity, cost efficiency, and latency red...

The article discusses the importance of using shader debugging information with NVIDIA Nsight Graphics for optimizing shader performance in ray tracing applications.

This article discusses the implementation of Video Multi-Method Assessment Fusion (VMAF) using NVIDIA GPUs and CUDA, highlighting the performance improvements and advantages of VMAF-CUDA over tradi...

This article discusses the emulation of the attention mechanism in transformer models using a fully convolutional network, specifically targeting improvements in computer vision tasks.

This article discusses inference optimization techniques for large language models (LLMs), highlighting the challenges and solutions associated with memory and compute efficiency.

The article discusses the intricacies of training Large Language Models (LLMs) using transformer networks, focusing on model architectures, attention mechanisms, and embedding techniques.