fal-serverless is a serverless Python runtime that lets you run and scale code in the cloud with no infra management.
With fal-serverless, you can build pipelines, serve ML models and scale them up to many users. You scale down to 0 when you don't use any resources.
fal-serverless supports custom compute resources including GPUs (A100s and T4).
Let's discover fal-serverless in less than 2 minutes.
Get started by installing
pip install fal-serverless
Login using the
fal-serverless auth login
Create a Python script
Create a new Python file, for example
In this file, define a decorated function that returns a joke:
from fal_serverless import isolated
Run your script
Run your script with
This should print out a joke, for example
How many programmers does it take to change a lightbulb? None, that's a hardware problem.
Congratulations! You have successfully run a function on
Ready for more?
See our examples.