We've cooked up a bunch of improvements designed to reduce friction and make the.



Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur.
Block quote
Ordered list
Unordered list
Bold text
Emphasis
Superscript
Subscript
We've just come out with a huge quality of life improvement to our Github integration that enables you to deploy to Serverless endpoints directly from Github rather than building and pushing your own Docker images.
Previously, if you ran into a problem with your deployment that required you to roll back, you would have to actually make those changes to your code itself in Github and force a new build down that would have to go through the entire testing and validation processes again. Functional, but clunky and hardly ideal, not to mention the fact that your endpoints would continue to serve the buggy code while the build was processing and workers were getting updated to the newest version afterwards.
Now, if you have to roll back for any reason, you can do so directly from the Builds tab of your serverless endpoint.

Important notes to consider when rolling back a release:
• Your endpoint immediately switches to the Docker image from the selected previous build.
• The rollback banner displays at the top of your endpoint page to indicate the current state.
• Your endpoint remains on the rolled-back version until you deploy a new release from GitHub.
• When you push a new commit and create a release, the new build automatically becomes the active version and supersedes the rollback.
Beyond the immediate technical benefits, this feature changes how you can approach deployments. With confidence that you can instantly roll back if needed, you can deploy more frequently and with less anxiety. This supports modern development practices like continuous deployment and incremental feature releases, where the ability to quickly reverse course is essential.If you'd like to read more, check out our docs on the new feature!

Deploy Serverless endpoints directly from GitHub and roll back instantly if needed. Runpod’s improved GitHub integration lets you revert to previous builds without rebuilding Docker images, enabling faster, safer, and more confident deployments.

We've just come out with a huge quality of life improvement to our Github integration that enables you to deploy to Serverless endpoints directly from Github rather than building and pushing your own Docker images.
Previously, if you ran into a problem with your deployment that required you to roll back, you would have to actually make those changes to your code itself in Github and force a new build down that would have to go through the entire testing and validation processes again. Functional, but clunky and hardly ideal, not to mention the fact that your endpoints would continue to serve the buggy code while the build was processing and workers were getting updated to the newest version afterwards.
Now, if you have to roll back for any reason, you can do so directly from the Builds tab of your serverless endpoint.

Important notes to consider when rolling back a release:
• Your endpoint immediately switches to the Docker image from the selected previous build.
• The rollback banner displays at the top of your endpoint page to indicate the current state.
• Your endpoint remains on the rolled-back version until you deploy a new release from GitHub.
• When you push a new commit and create a release, the new build automatically becomes the active version and supersedes the rollback.
Beyond the immediate technical benefits, this feature changes how you can approach deployments. With confidence that you can instantly roll back if needed, you can deploy more frequently and with less anxiety. This supports modern development practices like continuous deployment and incremental feature releases, where the ability to quickly reverse course is essential.If you'd like to read more, check out our docs on the new feature!
The most cost-effective platform for building, training, and scaling machine learning models—ready when you are.