How does this skill handle persistent data between runs?

The skill utilizes Modal Volumes, which provide persistent, high-performance storage that can be shared across functions and persists even after a container stops running.

Can I deploy web APIs using this skill?

Absolutely. You can use the @modal.web_endpoint decorator to turn any Python function into a live, auto-scaling HTTPS endpoint or integrate with FastAPI.

What types of GPUs are available through the Modal skill?

You can request various NVIDIA GPUs including the T4, L4, A100, L40S, H100, and the flagship B200 for high-performance training and inference.

Do I need a Modal account to use this skill?

Yes, you need a Modal account and an API token. You can sign up at modal.com, where new users typically receive free monthly credits to explore the platform.

Modal Cloud Computing

Name: Modal Cloud Computing
Author: jimmc414

byjimmc414

•

324

云基础设施

Deploys and manages serverless Python functions, GPU-accelerated ML models, and high-scale batch processing jobs in the cloud.

关于

This skill integrates the Modal serverless platform into Claude Code, allowing developers to execute Python functions on powerful cloud infrastructure with minimal configuration. It streamlines the deployment of machine learning models, handles GPU-intensive tasks like model training and inference, and automates scaling from zero to thousands of containers. By abstracting away infrastructure management, it enables AI-driven scientific discovery and high-performance computing directly within the Claude coding environment, making it ideal for workloads that require specialized hardware or distributed execution.

主要功能

324 GitHub stars
Secure secret management for protected API keys and environment variables
Automated autoscaling from zero to thousands of concurrent containers
Serverless GPU acceleration (H100, A100, B200) for ML workloads
Persistent storage management via Modal Volumes for large datasets and model weights
Deployment of serverless web endpoints, APIs, and scheduled cron jobs

使用场景

Running massive parallel data processing tasks across distributed cloud containers
Automating periodic scientific simulations, data backups, or model retraining
Deploying and scaling LLM inference or image generation models on high-end GPUs

关于

主要功能

324 GitHub stars
Secure secret management for protected API keys and environment variables
Automated autoscaling from zero to thousands of concurrent containers
Serverless GPU acceleration (H100, A100, B200) for ML workloads
Persistent storage management via Modal Volumes for large datasets and model weights
Deployment of serverless web endpoints, APIs, and scheduled cron jobs

使用场景

Running massive parallel data processing tasks across distributed cloud containers
Automating periodic scientific simulations, data backups, or model retraining
Deploying and scaling LLM inference or image generation models on high-end GPUs