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 ...
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...
19/03/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
19/03/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
19/03/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
19/03/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
19/03/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
19/03/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
19/03/2026
How Chris Bolte Builds the Sound of PlayStation Games Chris Bolte '16 is a technical sound designer at Sucker Punch Productions, where he helps create the...
18/03/2026
Newly named chief product officer (CPO), Larissa G rner Meeus will return to Net Insight on May 4.
Larissa G rner Meeus will become CPO of Net Insight on May 4...
18/03/2026
SVG Europe's The Football Summit 2026 explored how the sports broadcasting i...
18/03/2026
The 2026 NAB Show kicks off one month from today and SVG is once again set to cover the show from every angle. SVG's SportsTech@NAB Show Blog is now live - ...
18/03/2026
(L-R) The cast and crew of Dead Lover at The Ray Theater for its premiere at the 2025 Sundance Film Festival. (Photo by Robin Marshall/Shutterstock for Sundan...
18/03/2026
Yamaha C7 captured in Nashville
Wiltone Productions have announced the release of Music Row Piano, a deeply sampled Yamaha C7 piano library that's been ...
18/03/2026
Bass-enhancement plug-in upgraded
Along with a steady stream of new releases, Techivation have recently been revisiting some of the older plug-ins in their ...
18/03/2026
Mix-reference plug-in overhauled
iZotope's powerful mix-referencing plug-in has just reached its third major version, and now boasts a new capture proce...
18/03/2026
Latest EZKeys 2 expansion arrives
Toontrack's staggering collection of EZKeys 2 expansions has grown once again, and the latest instalment delivers a on...
18/03/2026
Jess Ho explores the politics of food in new SBS Audio podcast For The Culture
18 March, 2026
Media releases
New SBS Audio podcast For The Culture, hosted ...
18/03/2026
Future-ready broadcasts with ATSC 3.0 and enhanced services from Rohde & Schwarz...
18/03/2026
London Calling - When The Industry Convened to Help Streaming Find its MoJo In this blog, Laura Rognoni reflects on key discussions from the Connected TV World...
18/03/2026
SMPTE Unveils 2026 NAB Show Educational Presentations
Brie Clayton March 18, 2026
0 Comments
SMPTE , the home of media professionals, technologists, a...
18/03/2026
Auditel Ad Campaign Shot on Blackmagic PYXIS 12K
Brie Clayton March 18, 2026
0 Comments
LED wall virtual production blends 12K open gate acquisition w...
18/03/2026
Brainstorm transforms productivity and sustainability with Suite 7 at NAB Show 2...
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...
18/03/2026
X-Rite Pantone Demonstrates Advanced Color Management Solutions to Support Smart...
18/03/2026
Wednesday 18 March 2026
BAFTA winner James McAvoy to star in Sky Original serie...
18/03/2026
Wednesday 18 March 2026
Sky Sports and Zuffa Boxing announce multi-year agreement for the UK and Ireland
Sky Sports and Zuffa Boxing have announced a new mult...
18/03/2026
Wednesday 18 March 2026
Sky Unveils Poster and Trailer for Original Feature Fil...
Pinterest has engineered a way to serve its photo-sharing community more of the images they love.
