Launches
Coming soon
Upcoming launches to watch
Launch archive
Most-loved launches by the community
Launch Guide
Checklists and pro tips for launching
Products
News
Newsletter
The best of Product Hunt, every day
Stories
Tech news, interviews, and tips from makers
Changelog
New Product Hunt features and releases
Forums
Forums
Ask questions, find support, and connect
Streaks
The most active community members
Events
Meet others online and in-person
Advertise
Subscribe
Sign in
PyTorch
Machine learning library based on the Torch library
•
1 review
•
1 shoutout
•
53 followers
Visit website
Follow
Overview
Launches
Forums
Shoutouts
Reviews
Team
More
Blog
•
Newsletter
•
Questions
•
Forums
•
Product Categories
•
Apps
•
About
•
FAQ
•
Terms
•
Privacy and Cookies
•
X.com
•
Facebook
•
Instagram
•
LinkedIn
•
YouTube
•
Advertise
© 2025 Product Hunt
Maker Shoutouts
Testimonials from top launches
Trending
Sergii Shcherbak
used this to build
ContextGem
(103 points)
Industry-standard machine learning framework.
Helpful
Share
Report
6d ago
Dennis Ng
used this to build
Scam AI
(547 points)
A set of AI models is trained targeting different deepfake techniques with different custom made dataset with pytorch. We explored alternatives such as TensorFlow and Keras but chose PyTorch for its flexibility and dynamic computation graph.
Helpful
Share
Report
3mo ago
Bela Guy Pascal
used this to build
Spika.ai
(326 points)
Best for deeplearning and AI
Helpful
Share
Report
3mo ago
Ryan Tremblay
used this to build
Sonauto
(248 points)
When you're training a SOTA generative model with two people the giant wealth of existing GitHub Issues threads/reference codebases/etc is essential.
Helpful
Share
Report
4mo ago
Derek Yan
used this to build
AI Color Match
(87 points)
Defacto AI framework for building deep learning models
Helpful
Share
Report
2mo ago
Max Lund
used this to build
Jumper
(103 points)
ML hardware acceleration using CUDA for Nvidia GPUs on Windows, and via MPS and MLX frameworks for Apple silicon on macOS!
Helpful
Share
Report
6mo ago
Wladislav Radchenko
used this to build
Wunjo
(75 points)
Empowers project with efficient model development and deployment, including ONNX integration.
Helpful
Share
Report
11mo ago
