Run your ML workloads on GPUs without servers.
What it does
Guides the creation of Python workloads for GPU inference, training, and auto-scaling model APIs on Modal.
When to use it
Use for on-demand GPU workloads, auto-scaling model APIs, batch processing, or scheduled jobs without managing infrastructure.
How to use it
It changes how the agent implements and configures ML workloads by providing Modal code patterns and operational guidance.
What you provide
- An existing project
Uses
Good to know
- cannot be undone: Modal
Latest review
What you need · 2
Uses Python to define infrastructure and workload functions; no required local Python version is specified.
Uses the Modal Python package and CLI; declares modal>=0.64.0 and includes installation instructions.
Access · 1
This skill
Modal
Execute
Paid cloud GPU jobs (irreversible)
Execute
Installs the Modal package