The journey to create a state-of-the-art large language model (LLM) begins with a process called pretraining. Pretraining a state-of-the-art model is computationally demanding, with popular open-weights models featuring tens to hundreds of billions parameters and trained using trillions of tokens. As model intelligence grows with increasing model parameter count and training dataset size…
]]>The compute demands for large language model (LLM) inference are growing rapidly, fueled by the combination of growing model sizes, real-time latency requirements, and, most recently, AI reasoning. At the same time, as AI adoption grows, the ability of an AI factory to serve as many users as possible, all while maintaining good per-user experiences, is key to maximizing the value it generates.
]]>NVIDIA announced world-record DeepSeek-R1 inference performance at NVIDIA GTC 2025. A single NVIDIA DGX system with eight NVIDIA Blackwell GPUs can achieve over 250 tokens per second per user or a maximum throughput of over 30,000 tokens per second on the massive, state-of-the-art 671 billion parameter DeepSeek-R1 model. These rapid advancements in performance at both ends of the performance…
]]>As of March 18, 2025, NVIDIA Triton Inference Server is now part of the NVIDIA Dynamo Platform and has been renamed to NVIDIA Dynamo Triton, accordingly. The explosion of AI-driven applications has placed unprecedented demands on both developers, who must balance delivering cutting-edge performance with managing operational complexity and cost, and AI infrastructure.
]]>Meta’s Llama collection of open large language models (LLMs) continues to grow with the recent addition of Llama 3.3 70B, a text-only instruction-tuned model. Llama 3.3 provides enhanced performance respective to the older Llama 3.1 70B model and can even match the capabilities of the larger, more computationally expensive Llama 3.1 405B model on several tasks including math, reasoning, coding…
]]>Meta recently released its Llama 3.2 series of vision language models (VLMs), which come in 11B parameter and 90B parameter variants. These models are multimodal, supporting both text and image inputs. In addition, Meta has launched text-only small language model (SLM) variants of Llama 3.2 with 1B and 3B parameters. NVIDIA has optimized the Llama 3.2 collection of models for great performance and…
]]>As models grow larger and are trained on more data, they become more capable, making them more useful. To train these models quickly, more performance, delivered at data center scale, is required. The NVIDIA Blackwell platform, launched at GTC 2024 and now in full production, integrates seven types of chips: GPU, CPU, DPU, NVLink Switch chip, InfiniBand Switch, and Ethernet Switch.
]]>Deploying generative AI workloads in production environments where user numbers can fluctuate from hundreds to hundreds of thousands – and where input sequence lengths differ with each request – poses unique challenges. To achieve low latency inference in these environments, multi-GPU setups are a must – irrespective of the GPU generation or its memory capacity. To enhance inference performance in…
]]>Deploying large language models (LLMs) in production environments often requires making hard trade-offs between enhancing user interactivity and increasing system throughput. While enhancing user interactivity requires minimizing time to first token (TTFT), increasing throughput requires increasing tokens per second. Improving one aspect often results in the decline of the other…
]]>NVIDIA designed the NVIDIA Grace CPU to be a new kind of high-performance, data center CPU—one built to deliver breakthrough energy efficiency and optimized for performance at data center scale. Accelerated computing is enabling giant leaps in performance and energy efficiency compared to traditional CPU computing. To deliver these speedups, full-stack innovation at data center scale is…
]]>The continued growth of LLMs capability, fueled by increasing parameter counts and support for longer contexts, has led to their usage in a wide variety of applications, each with diverse deployment requirements. For example, a chatbot supports a small number of users at very low latencies for good interactivity. Meanwhile, synthetic data generation requires high throughput to process many items…
]]>Many of the most exciting applications of large language models (LLMs), such as interactive speech bots, coding co-pilots, and search, need to begin responding to user queries quickly to deliver positive user experiences. The time that it takes for an LLM to ingest a user prompt (and context, which can be sizable) and begin outputting a response is called time to first token (TTFT).
]]>In the latest round of MLPerf Inference – a suite of standardized, peer-reviewed inference benchmarks – the NVIDIA platform delivered outstanding performance across the board. Among the many submissions made using the NVIDIA platform were results using the NVIDIA GH200 Grace Hopper Superchip. GH200 tightly couples an NVIDIA Grace CPU with an NVIDIA Hopper GPU using NVIDIA NVLink-C2C…
]]>As large language models (LLMs) continue to grow in size and complexity, multi-GPU compute is a must-have to deliver the low latency and high throughput that real-time generative AI applications demand. Performance depends both on the ability for the combined GPUs to process requests as “one mighty GPU” with ultra-fast GPU-to-GPU communication and advanced software able to take full…
]]>The Llama 3.1 405B large language model (LLM), developed by Meta, is an open-source community model that delivers state-of-the-art performance and supports a variety of use cases. With 405 billion parameters and support for context lengths of up to 128K tokens, Llama 3.1 405B is also one of the most demanding LLMs to run. To deliver both low latency to optimize the user experience and high…
]]>Six years ago, we embarked on a journey to develop an AI inference serving solution specifically designed for high-throughput and time-sensitive production use cases from the ground up. At that time, ML developers were deploying bespoke, framework-specific AI solutions, which were driving up their operational costs and not meeting their latency and throughput service level agreements.
]]>Large language model (LLM) inference is a full-stack challenge. Powerful GPUs, high-bandwidth GPU-to-GPU interconnects, efficient acceleration libraries, and a highly optimized inference engine are required for high-throughput, low-latency inference. MLPerf Inference v4.1 is the latest version of the popular and widely recognized MLPerf Inference benchmarks, developed by the MLCommons…
]]>Large language models (LLM) are getting larger, increasing the amount of compute required to process inference requests. To meet real-time latency requirements for serving today’s LLMs and do so for as many users as possible, multi-GPU compute is a must. Low latency improves the user experience. High throughput reduces the cost of service. Both are simultaneously important. Even if a large…
]]>The exponential growth in data processing demand is projected to reach 175 zettabytes by 2025. This contrasts sharply with the slowing pace of CPU performance improvements. For more than a decade, semiconductor advancements have not kept up with the pace predicted by Moore’s Law, leading to a pressing need for more efficient computing solutions. NVIDIA GPUs have emerged as the most efficient…
]]>Today’s large language models (LLMs) are based on the transformer model architecture introduced in 2017. Since then, rapid advances in AI compute performance have enabled the creation of even larger transformer-based LLMs, dramatically improving their capabilities. Advanced transformer-based LLMs are enabling many exciting applications such as intelligent chatbots, computer code generation…
]]>As large language models (LLMs) continue to grow in size and complexity, the performance requirements for serving them quickly and cost-effectively continue to grow. Delivering high LLM inference performance requires an efficient parallel computing architecture and a flexible and highly optimized software stack. Recently, NVIDIA Hopper GPUs running NVIDIA TensorRT-LLM inference software set…
]]>Generative AI models have a variety of uses, such as helping write computer code, crafting stories, composing music, generating images, producing videos, and more. And, as these models continue to grow in size and are trained on even more data, they are producing even higher-quality outputs. Building and deploying these more intelligent models is incredibly compute-intensive…
]]>In the fast-evolving landscape of generative AI, the demand for accelerated inference speed remains a pressing concern. With the exponential growth in model size and complexity, the need to swiftly produce results to serve numerous users simultaneously continues to grow. The NVIDIA platform stands at the forefront of this endeavor, delivering perpetual performance leaps through innovations across…
]]>Generative AI is unlocking new computing applications that greatly augment human capability, enabled by continued model innovation. Generative AI models—including large language models (LLMs)—are used for crafting marketing copy, writing computer code, rendering detailed images, composing music, generating videos, and more. The amount of compute required by the latest models is immense and…
]]>Best-in-class AI performance requires an efficient parallel computing architecture, a productive tool stack, and deeply optimized algorithms. NVIDIA released the open-source NVIDIA TensorRT-LLM, which includes the latest kernel optimizations for the NVIDIA Hopper architecture at the heart of the NVIDIA H100 Tensor Core GPU. These optimizations enable models like Llama 2 70B to execute using…
]]>Large language models (LLMs) have seen dramatic growth over the last year, and the challenge of delivering great user experiences depends on both high-compute throughput as well as large amounts of high-bandwidth memory. NVIDIA TensorRT-LLM provides optimizations for both peak throughput and memory optimization, delivering massive improvements in LLM inference performance.
]]>The rapid growth in the size, complexity, and diversity of large language models (LLMs) continues to drive an insatiable need for AI training performance. Delivering top performance requires the ability to train models at the scale of an entire data center efficiently. This is achieved through exceptional craftsmanship at every layer of the technology stack, spanning chips, systems, and software.
]]>Generative AI is rapidly transforming computing, unlocking new use cases and turbocharging existing ones. Large language models (LLMs), such as OpenAI’s GPT models and Meta’s Llama 2, skillfully perform a variety of tasks on text-based content. These tasks include summarization, translation, classification, and generation of new content such as computer code, marketing copy, poetry, and much more.
]]>AI is transforming computing, and inference is how the capabilities of AI are deployed in the world’s applications. Intelligent chatbots, image and video synthesis from simple text prompts, personalized content recommendations, and medical imaging are just a few examples of AI-powered applications. Inference workloads are both computationally demanding and diverse, requiring that platforms be…
]]>In MLPerf Inference v3.0, NVIDIA made its first submissions to the newly introduced Network division, which is now part of the MLPerf Inference Datacenter suite. The Network division is designed to simulate a real data center setup and strives to include the effect of networking—including both hardware and software—in end-to-end inference performance. In the Network division…
]]>At the heart of the rapidly expanding set of AI-powered applications are powerful AI models. Before these models can be deployed, they must be trained through a process that requires an immense amount of AI computing power. AI training is also an ongoing process, with models constantly retrained with new data to ensure high-quality results. Faster model training means that AI-powered applications…
]]>The most exciting computing applications currently rely on training and running inference on complex AI models, often in demanding, real-time deployment scenarios. High-performance, accelerated AI platforms are needed to meet the demands of these applications and deliver the best user experiences. New AI models are constantly being invented to enable new capabilities…
]]>MLPerf benchmarks, developed by MLCommons, are critical evaluation tools for organizations to measure the performance of their machine learning models’ training across workloads. MLPerf Training v2.1—the seventh iteration of this AI training-focused benchmark suite—tested performance across a breadth of popular AI use cases, including the following: Many AI applications take advantage of…
]]>Today’s AI-powered applications are enabling richer experiences, fueled by both larger and more complex AI models as well as the application of many models in a pipeline. To meet the increasing demands of AI-infused applications, an AI platform must not only deliver high performance but also be versatile enough to deliver that performance across a diverse range of AI models.
]]>NVIDIA Grace CPU is the first data center CPU developed by NVIDIA. It has been built from the ground up to create the world’s first superchips. Designed to deliver excellent performance and energy efficiency to meet the demands of modern data center workloads powering digital twins, cloud gaming and graphics, AI, and high-performance computing (HPC), NVIDIA Grace CPU features 72 Armv9 CPU…
]]>MLPerf benchmarks are developed by a consortium of AI leaders across industry, academia, and research labs, with the aim of providing standardized, fair, and useful measures of deep learning performance. MLPerf training focuses on measuring time to train a range of commonly used neural networks for the following tasks: Lower training times are important to speed time to deployment…
]]>High-performance computing (HPC) has become the essential instrument of scientific discovery. Whether it is discovering new, life-saving drugs, battling climate change, or creating accurate simulations of our world, these solutions demand an enormous—and rapidly growing—amount of processing power. They are increasingly out of reach of traditional computing approaches.
]]>AI is transforming every industry, enabling powerful new applications and use cases that simply weren’t possible with traditional software. As AI continues to proliferate, and with the size and complexity of AI models on the rise, significant advances in AI compute performance are required to keep up. That’s where the NVIDIA platform comes in. With a full-stack approach spanning chips…
]]>