modal-serverless-gpu - Serverless GPU Cloud Platform for Machine Learning
Provides serverless GPU compute for running machine learning workloads, deploying auto-scaling APIs, and executing batch jobs.
Tags
Updated: 2026-09-20Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Deploy ML models as APIs
- Execute serverless GPU batch jobs
- Define infrastructure using Python code
- Mount persistent storage volumes
- Manage application secrets
- Schedule recurring cron tasks
Inputs
- Python source code
- Modal authentication token
- Container image definitions
- Model weights and datasets
Outputs
- Deployed API endpoints
- Function execution outputs
- Persisted volume storage data
- Execution logs
Requirements
- Python environment
- modal package version 0.64.0 or higher
- Authenticated Modal account