The Hao AI Lab research team at the University of California San Diego - at the forefront of pioneering AI model innovation - recently received an NVIDIA DGX B200 system to elevate their critical work in large language model inference.
Many LLM inference platforms in production today, such as NVIDIA Dynamo, use research concepts that originated in the Hao AI Lab, including DistServe.
How Is Hao AI Lab Using the DGX B200? Members of the Hao AI Lab standing with the NVIDIA DGX B200 system. With the DGX B200 now fully accessible to the Hao AI Lab and broader UC San Diego community at the School of Computing, Information and Data Sciences' San Diego Supercomputer Center, the research opportunities are boundless.
DGX B200 is one of the most powerful AI systems from NVIDIA to date, which means that its performance is among the best in the world, said Hao Zhang, assistant professor in the Hal c o lu Data Science Institute and department of computer science and engineering at UC San Diego. It enables us to prototype and experiment much faster than using previous-generation hardware.
Two Hao AI Lab projects the DGX B200 is accelerating are FastVideo and the Lmgame benchmark.
FastVideo focuses on training a family of video generation models to produce a five-second video based on a given text prompt - in just five seconds.
The research phase of FastVideo taps into NVIDIA H200 GPUs in addition to the DGX B200 system.
Lmgame-bench is a benchmarking suite that puts LLMs to the test using popular online games including Tetris and Super Mario Bros. Users can test one model at a time or put two models up against each other to measure their performance.
The illustrated workflow of Hao AI Lab's Lmgame-Bench project. Other ongoing projects at Hao AI Labs explore new ways to achieve low-latency LLM serving, pushing large language models toward real-time responsiveness.
Our current research uses the DGX B200 to explore the next frontier of low-latency LLM-serving on the awesome hardware specs the system gives us, said Junda Chen, a doctoral candidate in computer science at UC San Diego.
How DistServe Influenced Disaggregated Serving Disaggregated inference is a way to ensure large-scale LLM-serving engines can achieve the optimal aggregate system throughput while maintaining acceptably low latency for user requests.
The benefit of disaggregated inference lies in optimizing what DistServe calls goodput instead of throughput in the LLM-serving engine.
Here's the difference:
Throughput is measured by the number of tokens per second that the entire system can generate. Higher throughput means lower cost to generate each token to serve the user. For a long time, throughput was the only metric used by LLM-serving engines to measure their performance against one another.
While throughput measures the aggregate performance of the system, it doesn't directly correlate to the latency that a user perceives. If a user demands lower latency to generate the tokens, the system has to sacrifice throughput.
This natural trade-off between throughput and latency is what led the DistServe team to propose a new metric, goodput : the measure of throughput while satisfying the user-specified latency objectives, usually called service-level objectives. In other words, goodput represents the overall health of a system while satisfying user experience.
DistServe shows that goodput is a much better metric for LLM-serving systems, as it factors in both cost and service quality. Goodput leads to optimal efficiency and ideal output from a model.
How Can Developers Achieve Optimal Goodput? When a user makes a request in an LLM system, the system takes the user input and generates the first token, known as prefill. Then, the system creates numerous output tokens, one after another, predicting each token's future behavior based on past requests' outcomes. This process is known as decode.
https://blogs.nvidia.com/wp-content/uploads/2025/12/distserve.mp4
Prefill and decode have historically run on the same GPU, but the researchers behind DistServe found that splitting them onto different GPUs maximizes goodput.
Previously, if you put these two jobs on a GPU, they would compete with each other for resources, which could make it slow from a user perspective, Chen said. Now, if I split the jobs onto two different sets of GPUs - one doing prefill, which is compute intensive, and the other doing decode, which is more memory intensive - we can fundamentally eliminate the interference between the two jobs, making both jobs run faster.
This process is called prefill/decode disaggregation, or separating the prefill from decode to get greater goodput.
Increasing goodput and using the disaggregated inference method enables the continuous scaling of workloads without compromising on low-latency or high-quality model responses.
NVIDIA Dynamo - an open-source framework designed to accelerate and scale generative AI models at the highest efficiency levels with the lowest cost - enables scaling disaggregated inference.
In addition to these projects, cross-departmental collaborations, such as in healthcare and biology, are underway at UC San Diego to further optimize an array of research projects using the NVIDIA DGX B200, as researchers continue exploring how AI platforms can accelerate innovation.
Learn more about the NVIDIA DGX B200 system.
Most recent headlines
05/01/2027
Worlds first 802.15.4ab-UWB chip verified by Calterah and Rohde & Schwarz to be ...
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...
02/05/2026
Dalet, a leading technology and service provider for media-rich organizations, t...
01/05/2026
January 5 2026, 18:30 (PST) NBCUniversal's Peacock to Be First Streamer to ...
01/04/2026
January 4 2026, 18:00 (PST) DOLBY AND DOUYIN EMPOWER THE NEXT GENERATON OF CREATORS WITH DOLBY VISION
Douyin Users Can Now Create And Share Videos With Stun...
18/03/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
18/03/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
18/03/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
18/03/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
18/03/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
18/03/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
18/03/2026
SMPTE , the home of media professionals, technologists, and engineers, today unveiled its educational presentations for the 2026 NAB Show. This year SMPTE will ...
18/03/2026
Maxon, maker of powerful, approachable software solutions for creators working in 2D and 3D design, motion graphics, visual effects, gaming, and more, today ann...
18/03/2026
Digital Alert Systems
Preview
2026 NAB Show
April 19 - 22
Booth C3452
At the 2026 NAB Show, Digital Alert Systems will showcase Version 6.0 of its DASDEC ...
18/03/2026
Setplex today announced that it will showcase its complete, fully integrated Zapflex platform for the first time at the 2026 NAB Show, introducing powerful new ...
18/03/2026
THIS ANNOUNCEMENT RELATES TO THE DISCLOSURE OF INFORMATION THAT QUALIFIED OR MAY HAVE QUALIFIED AS INSIDE INFORMATION WITHIN THE MEANING OF ARTICLE 7(1) OF THE ...
18/03/2026
COW Jobs: Seeking DP for Low Budget Dramedy - Chicago
Brie Clayton March 17, 2026
0 Comments
Seeking Director of Photography for Low Budget Dramedy Fe...
18/03/2026
COW Jobs: Seeking Gaffer for Low Budget Dramedy - Chicago
Brie Clayton March 17, 2026
0 Comments
Seeking Gaffer for Low Budget Dramedy Feature Film- I...
18/03/2026
COW Jobs: Seeking Location, Sound for Low Budget Dramedy - Chicago
Brie Clayton March 17, 2026
0 Comments
Seeking Location/Sound for Low Budget Dramed...
18/03/2026
COW Jobs: Seeking Child Wrangler for Low Budget Film - Chicago
Brie Clayton March 17, 2026
0 Comments
Seeking Child Wrangler for Low Budget Dramedy Fe...
18/03/2026
Calrec Redefines Broadcast Workflows at NAB 2026 with its Most Powerful Hardware...
18/03/2026
Oscar Nominated Two People Exchanging Saliva Posted with DaVinci Resolve Studio
Brie Clayton March 17, 2026
0 Comments
DaVinci Resolve Studio handle...
18/03/2026
Boston Conservatory Presents Celebrated Musical Satire Urinetown Performances for this Center Stage production will take place at Boston Conservatory Theater ...
18/03/2026
Charlie Puth Joins Switched On Pop at Berklee NYC The Berklee alum spoke with host and Berklee NYC professor Charlie Harding for a live taping, answering audi...
17/03/2026
NASA+'s Rebecca Sirmons and Brittany Brown offer unique look at live streami...
17/03/2026
The transition to IP has fundamentally reshaped professional media infrastructures. Video, audio, and increasingly metadata now circulate as independent, precis...
17/03/2026
Live sports streaming can push every element in your video delivery chain to its limit, exposing every potential weakness in seconds. When the Super Bowl, the O...
17/03/2026
Texas Athletics sought to modernize its media production, enhance fan experience...
17/03/2026
Ikegami USA will demonstrate the latest additions to its wide range of broadcast...
17/03/2026
TNA Wrestling and iHeartMedia announces a new multi-platform collaboration that will integrate iHeartMedia across TNA's premium live events, weekly televisi...
17/03/2026
The goal was to transform Hard Rock Stadium into a global leader in sports and e...
17/03/2026
Spectrum has announced the launch of its new Multiview feature in the Spectrum TV App, giving customers the ability to watch up to four NCAA men's or women&...
17/03/2026
Genius Sports deal also covers data technology, AI, fan engagement, and performance analysis....
17/03/2026
Net Insight is supporting the rollout of a new state-wide centralized operation with Rede Massa, which is an SBT affiliate, the Brazilian regional television ne...
17/03/2026
Featuring audio from practice sessions, qualifying races, and Grand Prix races, the film represents Apple's sports-media ambitions
At Sunday night's Ac...
17/03/2026
Live broadcast has always been one of the most demanding environments in media a...
17/03/2026
DirecTV is introducing several new viewing features, including a multi-screen March Madness Mix channel and an updated Sports Central mobile app hub, ahead of...
17/03/2026
Deltatre has announced a multi-year partnership with ATP Media, the media arm of the ATP Tour, covering broadcast graphics, data, and production across the 2026...
17/03/2026
The Detroit Pistons have announced a third consecutive season partnering with Sc...
17/03/2026
Fresh Finds Africa spotlights emerging artists and movements across the continent and its global diaspora, with listeners tuning in to discover new Afro-forward...
17/03/2026
Last month, more than 60,000 fans piled into Bangkok's Rajamangala National ...
17/03/2026
Vintage-inspired channel strip joins line-up
Black Rooster Audio's latest plug-in provides an all-in-one mixing tool inspired by classic analogue consol...
17/03/2026
Level and EQ voice, reverb and noise independently
The latest plug-in to join Accentize's collection is said to take a new approach to dialogue processi...
17/03/2026
UHF radio mic & IEM bandwidth at risk
Once again, the UHF bandwidth that is currently allocated to RF audio gear is at risk of being reassigned to high-spee...
17/03/2026
Last Friday, the first Plant Fire Department Training Week in Bavaria successf...
17/03/2026
New campaign from NAATI and SBS CulturalConnnect highlights how we all deserve ...
17/03/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
17/03/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
17/03/2026
3D streaming infrastructure provider Miris today announced the launch of a public beta for its new 3D asset streaming platform. Miris is building the infrastruc...
The Hao AI Lab research team at the University of California San Diego - at the forefront of pioneering AI model innovation - recently received an NVIDIA DGX B200 system to elevate their critical work in large language model inference.
