
Large language models and the applications they power enable unprecedented opportunities for organizations to get deeper insights from their data reservoirs and to build entirely new classes of applications.
But with opportunities often come challenges.
Both on premises and in the cloud, applications that are expected to run in real time place significant demands on data center infrastructure to simultaneously deliver high throughput and low latency with one platform investment.
To drive continuous performance improvements and improve the return on infrastructure investments, NVIDIA regularly optimizes the state-of-the-art community models, including Meta's Llama, Google's Gemma, Microsoft's Phi and our own NVLM-D-72B, released just a few weeks ago.
Relentless Improvements Performance improvements let our customers and partners serve more complex models and reduce the needed infrastructure to host them. NVIDIA optimizes performance at every layer of the technology stack, including TensorRT-LLM, a purpose-built library to deliver state-of-the-art performance on the latest LLMs. With improvements to the open-source Llama 70B model, which delivers very high accuracy, we've already improved minimum latency performance by 3.5x in less than a year.
We're constantly improving our platform performance and regularly publish performance updates. Each week, improvements to NVIDIA software libraries are published, allowing customers to get more from the very same GPUs. For example, in just a few months' time, we've improved our low-latency Llama 70B performance by 3.5x.
NVIDIA has increased performance on the Llama 70B model by 3.5x. In the most recent round of MLPerf Inference 4.1, we made our first-ever submission with the Blackwell platform. It delivered 4x more performance than the previous generation.
This submission was also the first-ever MLPerf submission to use FP4 precision. Narrower precision formats, like FP4, reduces memory footprint and memory traffic, and also boost computational throughput. The process takes advantage of Blackwell's second-generation Transformer Engine, and with advanced quantization techniques that are part of TensorRT Model Optimizer, the Blackwell submission met the strict accuracy targets of the MLPerf benchmark.
Blackwell B200 delivers up to 4x more performance versus previous generation on MLPerf Inference v4.1's Llama 2 70B workload. Improvements in Blackwell haven't stopped the continued acceleration of Hopper. In the last year, Hopper performance has increased 3.4x in MLPerf on H100 thanks to regular software advancements. This means that NVIDIA's peak performance today, on Blackwell, is 10x faster than it was just one year ago on Hopper.
These results track progress on the MLPerf Inference Llama 2 70B Offline scenario over the past year. Our ongoing work is incorporated into TensorRT-LLM, a purpose-built library to accelerate LLMs that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM is built on top of the TensorRT Deep Learning Inference library and leverages much of TensorRT's deep learning optimizations with additional LLM-specific improvements.
Improving Llama in Leaps and Bounds More recently, we've continued optimizing variants of Meta's Llama models, including versions 3.1 and 3.2 as well as model sizes 70B and the biggest model, 405B. These optimizations include custom quantization recipes, as well as efficient use of parallelization techniques to more efficiently split the model across multiple GPUs, leveraging NVIDIA NVLink and NVSwitch interconnect technologies. Cutting-edge LLMs like Llama 3.1 405B are very demanding and require the combined performance of multiple state-of-the-art GPUs for fast responses.
Parallelism techniques require a hardware platform with a robust GPU-to-GPU interconnect fabric to get maximum performance and avoid communication bottlenecks. Each NVIDIA H200 Tensor Core GPU features fourth-generation NVLink, which provides a whopping 900GB/s of GPU-to-GPU bandwidth. Every eight-GPU HGX H200 platform also ships with four NVLink Switches, enabling every H200 GPU to communicate with any other H200 GPU at 900GB/s, simultaneously.
Many LLM deployments use parallelism over choosing to keep the workload on a single GPU, which can have compute bottlenecks. LLMs seek to balance low latency and high throughput, with the optimal parallelization technique depending on application requirements.
For instance, if lowest latency is the priority, tensor parallelism is critical, as the combined compute performance of multiple GPUs can be used to serve tokens to users more quickly. However, for use cases where peak throughput across all users is prioritized, pipeline parallelism can efficiently boost overall server throughput.
The table below shows that tensor parallelism can deliver over 5x more throughput in minimum latency scenarios, whereas pipeline parallelism brings 50% more performance for maximum throughput use cases.
For production deployments that seek to maximize throughput within a given latency budget, a platform needs to provide the ability to effectively combine both techniques like in TensorRT-LLM.
Read the technical blog on boosting Llama 3.1 405B throughput to learn more about these techniques.
Different scenarios have different requirements, and parallelism techniques bring optimal performance for each of these scenarios. The Virtuous Cycle Over the lifecycle of our architectures, we deliver significant performance gains from ongoing software tuning and optimization. These improvements translate into additional value for customers who train and deploy on our platforms. They're able to create more capable models and applications and deploy their existing models using less infrastructure, enhancing th
Most recent headlines
05/01/2027
Worlds first 802.15.4ab-UWB chip verified by Calterah and Rohde & Schwarz to be ...
04/08/2026
Dalet, a leading technology and service provider for media-rich organizations, t...
04/07/2026
April 7 2026, 19:00 (PDT) Detective Conan: Fallen Angel of the Highway Opens in...
01/06/2026
January 6 2026, 05:30 (PST) Dolby Sets the New Standard for Premium Entertainment at CES 2026
Throughout the week, Dolby brings to life the latest innovatio...
08/05/2026
NBC's 9:16 live-production workflows power Courtside Live, Rinkside Live, Vi...
08/05/2026
Native 1080p HDR productions will rely on a mix of remote workflows from Bristol and Los Angeles
Despite another prosperous WNBA season in 2025, there was no g...
08/05/2026
In-venue and creative video staffers at the professional and collegiate level ha...
08/05/2026
Players Era, an EverWonder Studio company, and ESPN have announced a multi-year ...
08/05/2026
BFBS (British Forces Broadcasting Service) has announced the selection of Syname...
08/05/2026
UFC and Joe Hand Promotions, UFC's exclusive commercial distributor in the U...
08/05/2026
Ease Live, an Evertz company, has announced it has been granted US Patent No. 12,556,777 for its graphical overlay technology for interactive live streaming. Th...
08/05/2026
Ateme has announced that VTVcab has deployed Ateme's OTT platform to power its VTVprime streaming service in Vietnam. The deployment covers live and on-dema...
08/05/2026
Amagi has announced the availability of its In-Content Ads offering via the Amagi ADS PLUS marketplace, providing programmatic access to ad formats inserted dir...
08/05/2026
Young broadcaster will deploy 11-camera complement, At the Line' scorebug f...
08/05/2026
Ratings Roundup is a rundown of recent rating news and is derived from press rel...
08/05/2026
FOX Sports, America's English-language home for the FIFA World Cup 2026, and...
08/05/2026
Molly Gordon and Ben Platt appear in Theater Camp. (Courtesy of Searchlight Pictures)
By Lucy Spicer
Her character is the beloved founder of the AdirondACTS...
08/05/2026
One-button synth generates random four-track ideas
Cyma Forma and French artist Bambounou have announced RND synth, a compact hardware synthesizer built aro...
08/05/2026
Portable four-layer granular and sampling instrument
Tasty Chips have announced the GR-2, a new granular synthesizer and sampling instrument that combines e...
08/05/2026
Video Show Report
Video of SUPERBOOTH 26: Polyend Drums
Polyends big announcement for Superbooth 2026 is the Drums, a new drum machine that features both ...
08/05/2026
Deal agreed as NI enters new chapter
Native Instruments CEO Nick Williams has announced that a definitive agreement has been signed for the company to be ac...
08/05/2026
Video Show Report
Video of SUPERBOOTH 26: Erica Bullfrog Drums
The Bullfrog Drums is the latest collaboration between Erica Synths and Richie Hawtin, and ...
08/05/2026
In our latest blog, Tim Pearson reflects on the recent launch of Play Snooker, the new digital home of snooker by the World Professional Billiards and Snooker A...
08/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
08/05/2026
Riedel Communications today announced its return as a sponsor of the Glasgow 2026 Commonwealth Games, where the company will serve as the Official Connectivity ...
08/05/2026
For the second straight year, Miri Technologies Inc. has been honored with a pair of coveted awards at the broadcast, media and entertainment industry's pre...
08/05/2026
Nine Alumni Nominated for Tony Awards More than 20 alumni contributed to this year's Tony-nominated productions.
May 7, 2026
By
Tori Donahue
Boston Co...
08/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
08/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
08/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
08/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
08/05/2026
Liberty University on why broadcast technology isn't just a technical invest...
08/05/2026
COW Jobs: UGC, On-Camera Video Content
Brie Clayton May 7, 2026
0 Comments
UGC, On-Camera Video Content
April 17, 2026Documentary Editor - US,......
08/05/2026
Wuppertal May 8, 2026
Riedel to Support Glasgow 2026 as Official Connectivity Integration Provider Riedel Communications today announced its return as a spons...
08/05/2026
Back to All News
Netflix Announces Standalone Sequel to Global Hit La Palma
Entertainment
08 May 2026
GlobalDenmarkFinlandNorwaySweden
Link copied to clipb...
08/05/2026
ICG is excited to share news of our official launch in Northern Ireland, marking a significant milestone in the agency's growth.
Led by Digital Marketing M...
08/05/2026
Over the past ten years, Thames Water, in partnership with Arqiva, has installed more than 1.2 million smart meters, creating one of the most extensive advanced...
07/05/2026
Journalists reporting on Sudan are working in one of the most complex and fast-m...
07/05/2026
Multi-year partnership positions Victory+ as a free home for Dallas Cowboys orig...
07/05/2026
From sideline reporting to directing and producing, the talented sophomore is building a well-rounded foundation for a career in live sports production
In the ...
07/05/2026
Cobalt Digital has received two Future Best of Show awards at NAB Show 2026. The COBALT blueCORE platform was recognized by TV Tech, and the COBALT PACIFIC ULL-...
07/05/2026
ESPN analyst Mina Kimes will host the televised semifinals and finals of the 202...
07/05/2026
Bitmovin has announced that MUBI, the global film streaming platform, has selected Bitmovin as its cloud VOD encoding partner. Bitmovin's encoding infrastru...
07/05/2026
NBCUniversal Telemundo Enterprises and the U.S. Soccer Federation have announced...
07/05/2026
Angel City Football Club (ACFC) and Victory have announced a regional broadcast partnership bringing live match coverage to fans across the greater Los Angeles...
07/05/2026
Spiideo has announced the launch of AI Highlights inside Spiideo Play, its automated sports production platform. AI Highlights combines video, event data, audio...
07/05/2026
Leostream Corporation has announced a unified remote access ecosystem for high-p...
07/05/2026
The Atlanta Dream has partnered with Victory to stream all locally broadcast Dream games for free, expanding the team's digital distribution strategy and g...
07/05/2026
Riedel Communications has announced the appointment of Marc Engroff as Chief Fin...
07/05/2026
SES and ARD, Germany's largest public broadcasting network, have announced a long-term extension of their satellite distribution partnership through 2039. U...