Sony Pixel Power calrec Sony

NVIDIA Hopper Leaps Ahead in Generative AI at MLPerf

27/03/2024

It's official: NVIDIA delivered the world's fastest platform in industry-standard tests for inference on generative AI.

In the latest MLPerf benchmarks, NVIDIA TensorRT-LLM - software that speeds and simplifies the complex job of inference on large language models - boosted the performance of NVIDIA Hopper architecture GPUs on the GPT-J LLM nearly 3x over their results just six months ago.

The dramatic speedup demonstrates the power of NVIDIA's full-stack platform of chips, systems and software to handle the demanding requirements of running generative AI.

Leading companies are using TensorRT-LLM to optimize their models. And NVIDIA NIM - a set of inference microservices that includes inferencing engines like TensorRT-LLM - makes it easier than ever for businesses to deploy NVIDIA's inference platform.

Raising the Bar in Generative AI TensorRT-LLM running on NVIDIA H200 Tensor Core GPUs - the latest, memory-enhanced Hopper GPUs - delivered the fastest performance running inference in MLPerf's biggest test of generative AI to date.

The new benchmark uses the largest version of Llama 2, a state-of-the-art large language model packing 70 billion parameters. The model is more than 10x larger than the GPT-J LLM first used in the September benchmarks.

The memory-enhanced H200 GPUs, in their MLPerf debut, used TensorRT-LLM to produce up to 31,000 tokens/second, a record on MLPerf's Llama 2 benchmark.

The H200 GPU results include up to 14% gains from a custom thermal solution. It's one example of innovations beyond standard air cooling that systems builders are applying to their NVIDIA MGX designs to take the performance of Hopper GPUs to new heights.

Memory Boost for NVIDIA Hopper GPUs NVIDIA is sampling H200 GPUs to customers today and shipping in the second quarter. They'll be available soon from nearly 20 leading system builders and cloud service providers.

H200 GPUs pack 141GB of HBM3e running at 4.8TB/s. That's 76% more memory flying 43% faster compared to H100 GPUs. These accelerators plug into the same boards and systems and use the same software as H100 GPUs.

With HBM3e memory, a single H200 GPU can run an entire Llama 2 70B model with the highest throughput, simplifying and speeding inference.

GH200 Packs Even More Memory Even more memory - up to 624GB of fast memory, including 144GB of HBM3e - is packed in NVIDIA GH200 Superchips, which combine on one module a Hopper architecture GPU and a power-efficient NVIDIA Grace CPU. NVIDIA accelerators are the first to use HBM3e memory technology.

With nearly 5 TB/second memory bandwidth, GH200 Superchips delivered standout performance, including on memory-intensive MLPerf tests such as recommender systems.

Sweeping Every MLPerf Test On a per-accelerator basis, Hopper GPUs swept every test of AI inference in the latest round of the MLPerf industry benchmarks.

In addition, NVIDIA Jetson Orin remains at the forefront in MLPerf's edge category. In the last two inference rounds, Orin ran the most diverse set of models in the category, including GPT-J and Stable Diffusion XL.

The MLPerf benchmarks cover today's most popular AI workloads and scenarios, including generative AI, recommendation systems, natural language processing, speech and computer vision. NVIDIA was the only company to submit results on every workload in the latest round and every round since MLPerf's data center inference benchmarks began in October 2020.

Continued performance gains translate into lower costs for inference, a large and growing part of the daily work for the millions of NVIDIA GPUs deployed worldwide.

Advancing What's Possible Pushing the boundaries of what's possible, NVIDIA demonstrated three innovative techniques in a special section of the benchmarks called the open division, created for testing advanced AI methods.

NVIDIA engineers used a technique called structured sparsity - a way of reducing calculations, first introduced with NVIDIA A100 Tensor Core GPUs - to deliver up to 33% speedups on inference with Llama 2.

A second open division test found inference speedups of up to 40% using pruning, a way of simplifying an AI model - in this case, an LLM - to increase inference throughput.

Finally, an optimization called DeepCache reduced the math required for inference with the Stable Diffusion XL model, accelerating performance by a whopping 74%.

All these results were run on NVIDIA H100 Tensor Core GPUs.

A Trusted Source for Users MLPerf's tests are transparent and objective, so users can rely on the results to make informed buying decisions.

NVIDIA's partners participate in MLPerf because they know it's a valuable tool for customers evaluating AI systems and services. Partners submitting results on the NVIDIA AI platform in this round included ASUS, Cisco, Dell Technologies, Fujitsu, GIGABYTE, Google, Hewlett Packard Enterprise, Lenovo, Microsoft Azure, Oracle, QCT, Supermicro, VMware (recently acquired by Broadcom) and Wiwynn.

All the software NVIDIA used in the tests is available in the MLPerf repository. These optimizations are continuously folded into containers available on NGC, NVIDIA's software hub for GPU applications, as well as NVIDIA AI Enterprise - a secure, supported platform that includes NIM inference microservices.

The Next Big Thing The use cases, model sizes and datasets for generative AI continue to expand. That's why MLPerf continues to evolve, adding real-world tests with popular models like Llama 2 70B and Stable Diffusion XL.

Keeping pace with the explosion in LLM model sizes, NVIDIA founder and CEO Jensen Huang announced last week at GTC that the NVIDIA Blackwell architecture GPUs will deliver new levels of performance required for the multitrillion-parameter AI models.

Inference for large language models is difficult, requiring both e
LINK: https://blogs.nvidia.com/blog/tensorrt-llm-inference-mlperf/...
See more stories from nvidia

More from Nvidia

19/11/2026

Season's Streamings and Savings: Black Friday Deals Come to GeForce NOW

GeForce NOW is kicking off Black Friday with more reasons to make time for gaming. Six-month memberships are back for a limited time. Save 30% on the first six-...

18/11/2026

NVIDIA RTX Spark Compact Desktops Out Now

New NVIDIA RTX Spark compact desktops from ASUS, Dell and MSI are available today, bringing local AI agents, image and video generation, and model fine-tuning t...

17/11/2026

Ian Buck Kicks Off NVIDIA's Week at SC26 as Science Enters the Age of Agents

NVIDIA's Ian Buck kicked off the company's week at SC26 in Chicago on Monday with new tools for AI agents, software that can plan experiments, run code ...

16/11/2026

NVIDIA DGX Spark Developer Kit Turns a Desk Into a Supercomputing Lab

At SC26, an annual supercomputing conference taking place this week in Chicago, NVIDIA is introducing the DGX Spark HPC Developer Kit for researchers, academics...

16/11/2026

NVIDIA Announces Rubin HPC - A New GPU to Accelerate Agents for Science, Engineering and Analytics

Announced today at SC26, NVIDIA Rubin HPC is a new GPU in the NVIDIA Vera Rubin ...

16/11/2026

CUDA at 20: How the Platform Transformed Scientific Computing

This week at SC26, NVIDIA is marking two decades of CUDA by honoring the researchers, developers and engineers who helped make GPU computing a foundation for mo...

16/11/2026

NVIDIA CUDA-X Libraries Give Agents the Tools to Accelerate Scientific Discovery

With expanded NVIDIA CUDA-X libraries, including cuPhoton, cuPotential and cuSpa, researchers can sift through vast amounts of data to accelerate research, from...

16/11/2026

NVIDIA Sweeps MLPerf Training and Endpoints as Vera Rubin Debuts With Leading Performance

In its MLPerf benchmarks debut, with results released today, the NVIDIA Vera Rub...

16/11/2026

NVIDIA Expands Slurm to Bring Quantum Computing Into Supercomputing

Quantum processor deployments at supercomputing centers have grown nearly sevenfold over the past five years, with nearly 30 supercomputing centers around the w...

16/11/2026

Lambda Boosts AI Factory Resiliency and Efficiency With NVIDIA Photonics

To train an AI model, thousands of GPUs have to work together, requiring a network that's fast, efficient and resilient. Lambda is tackling the network pie...

15/11/2026

AI Day Seoul Brings Together Korea's Industry Leaders, Startups and Developer Communities

Over two days at COEX, more than 2,000 attendees converged for AI Day Seoul, bri...

13/11/2026

How AI Is Helping Care Teams Get Patients the Right Care, Sooner

From pediatric research to smart hospitals, AI is helping care teams spend less time on routine tasks and more time with patients. Health systems and startups...

12/11/2026

A New Dawn in the Cloud: Warhammer 40,000: Dawn of War IV' Is Coming to GeForce NOW

Rally the ranks this GFN Thursday. Warhammer 40,000: Dawn of War IV is coming to...

10/11/2026

NVIDIA Expands Open Source Commitment With OpenShell Donation and New AI Infrastructure

Kubernetes, the open source system that manages how applications run across thou...

09/11/2026

NVIDIA Announces New Planned Investments in Korean Startups at the MSIT-NVIDIA AI Startup Partnership Forum

Korea's Ministry of Science and ICT and NVIDIA hosted the MSIT-NVIDIA AI Sta...

09/11/2026

Practice Makes Precise: At CoRL, NVIDIA and Partners Reveal How Robots Rehearse Delicate Work in Simulation

Simulation, which has long been the proving ground for robots learning to walk, ...

08/11/2026

NVIDIA Dynamo Recipes Bring Korea's Leading Open Models to Production

NVIDIA is releasing Dynamo-optimized deployment recipes for Korea's leading open models: A.X K2 from SK Telecom, K-EXAONE 2.0 from LG AI Research, Solar Ope...

08/11/2026

From Chips to Skills, NVIDIA and Korea Expand Sovereign AI Collaboration

NVIDIA and Korea's Ministry of Science and ICT (MSIT) are expanding their collaboration across the country's sovereign AI ecosystem, from AI semiconduct...

08/11/2026

Korea's AI Ecosystem Advances and Secures Agentic AI With NVIDIA

As AI agents take on more work, they need capable open models and security that advances alongside them. Hyundai Motor Group is exploring NVIDIA NemoClaw bluep...

08/11/2026

Korea Advances Physical AI Across Industries With NVIDIA

Tapping into the country's strengths in manufacturing and engineering, NVIDIA is helping advance Korea's physical AI ecosystem. The country's indu...

06/11/2026

How NVIDIA Open Source Tools Are Helping Researchers Build Next-Generation 6G Networks

A year ago, NVIDIA open sourced its Aerial wireless software, joining Sionna and...

05/11/2026

Vera Delivers the Best of Both Worlds: Highest Throughput and Fastest Agents

AI agents do more than generate answers. They search for information, query databases, write and test code and take action. Each of those steps relies on a CP...

05/11/2026

More Performance From Every Byte: How Full-Stack Codesign Solves AI's Memory Challenge

Larger models, longer contexts and agentic applications are increasing GPU memor...

05/11/2026

The Wizard of Open Weights: Chris Alexiuk Makes AI Easy With Open Models

Chris Alexiuk has a simple rule about open source AI: If you believe in it, be loud about it. We should be shouting about this technology from the rooftops, ...

05/11/2026

Hogwarts Legacy' Gets a Magical NVIDIA DLSS 5 Upgrade on GeForce NOW

Hogwarts Legacy receives an NVIDIA DLSS 5 upgrade with 3D-Guided Neural Rendering today, bringing lifelike lighting and materials to the wizarding world on GeFo...

03/11/2026

AI Is Changing How Semiconductor Fabs Work - and Engineers Are Moving Faster Because of It

Demand for advanced chips is rising. The processes to build them are getting mor...

02/11/2026

Cities Worldwide Build and Scale AI Services With NVIDIA Physical and Agentic AI

Cities generate enormous amounts of data from cameras, sensors and operational systems, but turning it into useful action - for planning, maintenance and public...

30/10/2026

Things That Go Beep in the Night: Agentic AI Joins the Search for Extraterrestrial Signals

While science fiction lore tells us that humans will meet extraterrestrial life ...

29/10/2026

Slice Into GFN Thursday: Phantom Blade Zero' Launches on GeForce NOW

This Halloween week, GFN Thursday is delivering a fresh batch of gaming treats. Something wicked this blade comes. S-GAME's Phantom Blade Zero launches on ...

28/10/2026

NVIDIA RTX Spark Windows Laptops Gain New Models, Agent Tools and Games

NVIDIA RTX Spark powers thin and light laptops built for everything that developers, creators and gamers do. RTX Spark laptops are now available from ASUS, Del...

27/10/2026

How AI Is Changing the Pace of Discovery for Millions Living With Dementia

There are 57 million people worldwide living with dementia today. For the researchers working to help them, the obstacle isn't a lack of effort - it's t...

22/10/2026

Kazakhstan Expands Compute for Its AI Future

Kazakhstan's AI ecosystem is moving from infrastructure plans to deployment. The shift is visible across the full AI stack - from infrastructure to models...

22/10/2026

NVIDIA Unveils Minerva to Bring End-to-End Observability for AI Factories

Launched today, NVIDIA Minerva is an AIOps platform built to help teams find problems earlier and keep AI factories productive. It brings together telemetry fro...

22/10/2026

Cloud Deployment Incoming: Call of Duty: Modern Warfare 4' Arrives on GeForce NOW

Lock in and load out this GFN Thursday. Call of Duty: Modern Warfare 4 arrives o...

21/10/2026

NVIDIA Open Models Power a New Wave of European Public Sector Projects

Governments need modern solutions to serve the public while keeping sensitive information under their control. Open models provide a path forward, letting gove...

21/10/2026

Pioneers Across Europe Deploy NVIDIA Earth-2 Open Models to Power Real-World Weather and Climate Prediction

Weather forecasts shape more than daily plans; timely weather information is cru...

21/10/2026

NVIDIA Transforms European Retail, From Digital Discovery to Physical Operations

European retailers are using open models and physical intelligence across use cases - from a commerce platform cutting inference costs by 90% to to a fulfillmen...

21/10/2026

How Companies Are Using NVIDIA DSX to Break the Power Bottleneck

Companies around the world are building on the NVIDIA DSX AI Factory Platform to plan, simulate and run the grid and the AI factory as one system, from the subs...

21/10/2026

NVIDIA Cosmos Opens New Tools to Train, Evaluate and Deploy World Models

To help developers rapidly build world models, which help physical AI systems understand and simulate the real world, NVIDIA has expanded the Cosmos platform wi...

21/10/2026

Leading European Financial Services Organizations Embrace Open Models to Build Proprietary Intelligence

At GTC Berlin, banks, payment companies and financial data providers are showing...

21/10/2026

NVIDIA Confidential Computing Expands, Enabling Frontier Model Builders to Securely Scale Across Global Infrastructure

NVIDIA builds tools to enable safe agents across the stack. The NVIDIA OpenShell...

21/10/2026

NVIDIA cuDSS Now Generally Available to Accelerate Engineering and Scientific Simulations

NVIDIA cuDSS, launched today in general availability, is an NVIDIA CUDA-X librar...

21/10/2026

Europe's Industrial Leaders Reinvent Engineering and Manufacturing With NVIDIA

To increase productivity, accelerate innovation and create new opportunities for...

21/10/2026

NVIDIA Cloud Partners Scale Across Europe - Sovereign, Open and Built for Safe AI Agents

Demand from AI-natives is pulling the European AI cloud ecosystem forward faster...

21/10/2026

Google Cloud and NVIDIA Announce General Availability of NVIDIA Vera Rubin Infrastructure

General availability of the instances is coming next month, with planned expansi...

21/10/2026

Bringing the Spark to Europe: Local Intelligence Powers Next Wave of Agents

At GTC Berlin, NVIDIA is showcasing its full lineup of local AI hardware. RTX Spark, which launched last week, powers personal agents on Windows PCs; DGX Spark ...

19/10/2026

Germany Wants to Lead the World in Industrial AI: How NVIDIA Will Help

In the cavernous hall of Kraftwerk, a former power station in Berlin, German Chancellor Friedrich Merz and NVIDIA founder and CEO Jensen Huang sat down to discu...

19/10/2026

Spain-Based Startups Advance Regional Innovation With Barcelona Supercomputing Center

The Barcelona Supercomputing Center (BSC)'s AI Factory Accelerator Programme...

19/10/2026

NVIDIA Advances Agentic Security for Media, From European Public Service Broadcasting to Global Content Production

At a creative industry event that took place today in Berlin - hosted in collabo...

17/10/2026

RTX Spark Ignites Global Celebration as New Windows PCs Arrive

NVIDIA RTX Spark laptops are now available, bringing NVIDIA Blackwell RTX graphics, up to 128GB of unified memory and the full NVIDIA AI platform to slim, premi...