Hosted Service
Inference & ServingAutomation & Integration
Modal
1Run 2Python 3code 4and 5models 6serverlessly.
the six Ws · specification
W1
Who
By Modal Labs.
W2
What
Serverless cloud for running Python functions and model inference on GPUs.
W3
Where
A hosted platform driven from Python.
W4
When
When you need on-demand GPU compute.
W5
Why
Deploy GPU workloads without managing servers.
W6
With
A Modal account and the Python SDK.
W7
Watch
Commercial serverless platform, account required; your code runs on Modal's cloud.
ServerlessGPUPython