
Pinterest has engineered a way to serve its photo-sharing community more of the images they love.
The social-image service, with more than 400 million monthly active users, has trained bigger recommender models for improved accuracy at predicting people's interests.
Pinterest handles hundreds of millions of user requests an hour on any given day. And it must also narrow down relevant images from roughly 300 billion images on the site to roughly 50 for each person.
The last step - ranking the most relevant and engaging content for everyone using Pinterest - required a leap in acceleration to run heftier models, with minimal latency, for better predictions.
Pinterest has improved the accuracy of its recommender models powering people's home feeds and other areas, increasing engagement by as much as 16%.
The leap was enabled by switching from CPUs to NVIDIA GPUs, which could easily be applied next to other areas, including advertising images, according to Pinterest.
Normally we would be happy with a 2% increase, and 16% is just a beginning for home feeds. We see additional gains - it opens a lot of doors for opportunities, said Pong Eksombatchai, a software engineer at Pinterest.
Transformer models capable of better predictions are shaking up industries from retail to entertainment and advertising. But their leaps in performance gains of the past few years have come with a need to serve models that are some 100x bigger as their number of model parameters and computations skyrockets.
Huge Inference Gains, Same Infrastructure Cost Like many, Pinterest engineers wanted to tap into state-of-the-art recommender models to increase engagement. But serving these massive models on CPUs presented a 100x increase in cost and latency. That wasn't going to maintain its magical user experience - fresh and more appealing images - occurring within a fraction of a second.
If that latency happened, then obviously our users wouldn't like that very much because they would have to wait forever, said Eksombatchai. We are pretty close to the limit of what we can do on CPU basically.
The challenge was to serve these hundredfold larger recommender models within the same cost and latency constraints.
Working with NVIDIA, Pinterest engineers began architectural changes to optimize their inference pipeline and recommender models to enable the transition from CPU to GPU cloud instances. The technology transition began late last year and required major changes to how the company manages workloads. The result is a 100x gain in inference efficiency on the same IT budget, meeting their goals.
We are starting to use really, really big models now. And that is where the GPU comes in - to help make these models possible, Eksombatchai said.
Tapping Into cuCollections Switching from CPUs to GPUs required rethinking its inference systems architecture. Among other issues, engineers had to change how they send workloads to their inference servers. Fortunately, there are tools to assist in making the transition easier.
The Pinterest inference server built for CPUs had to be altered because it was set up to send smaller batch sizes to its servers. GPUs can handle much larger workloads, so it's necessary to set up larger batch requests to increase efficiency.
One area where this comes into play is with its embedding table lookup module. Embedding tables are used to track interactions between various context-specific features and interests of user profiles. They can track where you navigate, and what people Pin on Pinterest, share or numerous other actions, helping refine predictions on what users might like to click on next.
They are used to incrementally learn user preference based on context in order to make better content recommendations to those using Pinterest. Its embedding table lookup module required two computation steps repeated hundreds of times because of the number of features tracked.
Pinterest engineers greatly reduced this number of operations using a GPU-accelerated concurrent hash table from NVIDIA cuCollections. And they set up a custom consolidated embedding lookup module so they could merge requests into a single lookup. Better results were seen immediately.
Using cuCollections helped us to remove bottlenecks, said Eksombatchai.
Enlisting CUDA Graphs Pinterest relied on CUDA Graphs to eliminate what was remaining of the small batch operations, further optimizing its inference models.
CUDA Graphs helps reduce the CPU interactions when launching on GPUs. They're designed to enable workloads to be defined as graphs rather than single operations. They provide a mechanism to launch multiple GPU operations through a single CPU operation, reducing CPU overheads.
Pinterest enlisted CUDA Graphs to represent the model inference process as a static graph of operation instead of as those individually scheduled. This enabled the computation to be handled as a single unit without any kernel launching overhead.
The company now supports CUDA Graph as a new backend of its model server. When a model is first loaded, the model server runs the model inference once to build the graph instance. This graph can then be run repeatedly in inference to show content on its app or site.
Implementing CUDA Graphs helped Pinterest to significantly reduce inference latency of its recommender models, according to its engineers.
GPUs have enabled Pinterest to do something that was impossible with CPUs on the same budget, and by doing this they can make changes that have a direct impact on various business metrics.
Learn about Pinterest's GPU-driven inference and optimizations at its GTC session, Serving 100x Bigger Recommender Models, and in the Pinterest Engineering blog.
Register for GTC, running Sept. 19-22, for free to attend sessions with NVIDIA and dozens of industry leaders.
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...
06/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
06/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
06/05/2026
DARTFORD, UNITED KINGDOM, MAY 5, 2026 When live cycling races and international marathons stretch for miles across cities and countryside, there is no margin ...
06/05/2026
Oberkochen/Germany, May 5, 2026
ZEISS announces the launch of CinCraft LensCore, a novel solution for creating physically based cinematic lens looks for visual...
06/05/2026
How changes to proteins can alter drug interactions for new precision therapies Scripps Research team maps how chemical modifications to proteins affect drug bi...
05/05/2026
Experts from the world of academia, tech, business, politics and media convened for a Thomson Talks at the Cambridge Disinformation Summit in April. It's th...
05/05/2026
Three phones were hardwired for power and transmission to the truck; camera feat...
05/05/2026
The creative studio behind campaigns for the NBA, Fanatics Sportsbook & Casino, ...
05/05/2026
Nielsen has announced results from a co-viewing pilot program covering February&...
05/05/2026
viztrick AiDi, an on-device AI solution developed by Nippon TV, delivered global...
05/05/2026
ARRI has announced Omnibar, a battery-powered, IP65-rated multi-color LED linear...
05/05/2026
Imagine Communications has announced that France T l visions is the first broadc...
05/05/2026
The Women's National Basketball Association (WNBA) and Bell Media today announced a multiyear agreement to broadcast and stream WNBA games in Canada beginni...
05/05/2026
SVG is proud to announce Warner Bros. Discovery's Techwood Studios in Atlant...
05/05/2026
With no operator required, AutoMic workflow automates talent identification on U...
05/05/2026
A crash in 2015 set the industry back, but this winter proved that drones are he...
05/05/2026
Another year, and more proof that Asia continues to shape some of the world's most exciting new sounds. This year's RADAR artists draw from deep local r...
05/05/2026
The Austin City Limits Music Fest 2026 lineup just dropped, and this year, Spoti...
05/05/2026
New drum machine book campaign incoming
Bjooks have announced that during Superbooth 2026, they will be launching a Kickstarter campaign to fund the product...
05/05/2026
Flagship all-in-one production bundle updated
The latest version of Native Instruments' flagship virtual instrument and plug-in bundle has just been ann...
05/05/2026
Rohde & Schwarz to host RF Testing Innovations Forum 2026, helping design engine...
05/05/2026
L3Harris provides communications, electronic warfare, sensors and mission systems that enable Virginia-class submarine crews to operate with confidence in conte...
05/05/2026
The company grew by 7.6% in net revenue and 16.3% in EBITDA, achieving a 33% inc...
05/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
05/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
05/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
05/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
05/05/2026
Project Marks First Major Broadcast Deployment of Latest Addition to SNP Lineup
Imagine Communications today announced that France T l visions is the first br...
05/05/2026
Shotoku Broadcast Systems Wins 2026 NAB Show Product of the Year Award
Shotoku Broadcast Systems announced today that its Swoop range of robotic cranes has be...
05/05/2026
DigitalGlue's creative.space Intelligence Wins Future's Best of Show Award, Presented by TV Tech
creative.space Intelligence (CSI), part of the creativ...
05/05/2026
Zixi, a leader in live video delivery and workflow orchestration, will showcase next-generation broadcast workflows at the Media Production and Technology Show ...
05/05/2026
Stingr marks its launch with a new approach to second-screen interactivity
Brie Clayton May 5, 2026
0 Comments
Huge leap forward in revenues and engag...
05/05/2026
Shotoku Broadcast Systems Wins 2026 NAB Show Product of the Year Award
Brie Clayton May 5, 2026
0 Comments
Shotoku Broadcast Systems announced today tha...
05/05/2026
Following a successful NAB Show in Las Vegas, DHD will promote examples from its wide range of broadcast-quality audio production equipment at the May 13th-14th...
05/05/2026
LucidLink today announced its programme for MPTS 2026, where it will exhibit at Stand M59 at Olympia London, 13 to 14 May. The company will showcase its latest ...
05/05/2026
Limecraft today announces the release of Limecraft 2026.3, the third platform update in its 2026 release cycle. Limecraft is an AI-powered production platform t...
05/05/2026
Huge leap forward in revenues and engagement...
05/05/2026
Broadcast Solutions, a leading system integrator and provider of innovative solutions for the broadcast media industry, has taken another significant step in st...
05/05/2026
Operative today announced the appointment of Dang Ly as Chief Product Officer, signaling the company's accelerating commitment to delivering the next genera...
05/05/2026
The Media Talent Manifesto (MTM) today announces the return of the World Skills Caf at IBC2026, positioning the event as a critical industry forum to confront ...
05/05/2026
ARRI unveils Omnibar: compact, modular, battery-powered IP65 LED bars with preci...
05/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
05/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
05/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
05/05/2026
Digital Domain Welcomes Award-Nominated VFX Supervisor Jelmer Boskma
Brie Clayton May 4, 2026
0 Comments
Digital Domain, a global leader in visual eff...
05/05/2026
Enterprise AI has learned to generate. It has learned to reason. Now companies are asking the next question: How should AI act?
Early agent systems have shown ...