Deploy AI/ML models and workflows on Modal's cloud platform.
npx skills add https://github.com/tassiovale/claude-code-kit --skill modal-tassiovale
Please help me install this Agent Skill. Skill: modal Source: https://github.com/tassiovale/claude-code-kit/tree/main/skills/modal Command: npx skills add https://github.com/tassiovale/claude-code-kit --skill modal-tassiovale
This Skill enables deploying and running AI/ML models and workflows on Modal's cloud platform, simplifying the process of serving models, scaling Python code, and scheduling jobs.
Deploy a Python script to run on Modal and serve a model using the Modal Python SDK:
import modal
app = modal.App("my-app")
@app.function(gpu="H100")
def predict(text: str):
# Run model inference
return "Model prediction result"
modal deploy script.py
High-intent search queries and answers about installing and using this skill.
Yes, you can run serverless Python code on custom container images by deploying scripts to Modal. This allows you to scale Python workflows serverlessly while maintaining your specific environment dependencies.
You can schedule jobs to retrain machine learning models at regular intervals by configuring Modal scheduled jobs. This automates your machine learning workflows based on specific time criteria or intervals.
Yes, you need the Modal Python SDK to serve predictions with GPUs. You must configure your credentials and environment variables to deploy functions that utilize GPUs like the H100 for model inference.
The best way to scale Python code for serverless computing is deploying it as autoscaling functions on Modal. This approach handles custom containers and scheduled jobs without managing underlying infrastructure.
Limitations when using custom container images with serverless functions include the requirement to configure specific credentials and environment variables within the Modal Python SDK before deployment.
JuanMS20Configure GitHub authentication for Hermes Agent using git, gh CLI, or SSH credentials.
gaiastudio-aiRun automated accessibility tests on deployed web applications with axe-core, pa11y, and Lighthouse.
felixboehmRun Python functions serverlessly in the cloud with autoscaling containers and GPU support.
519labDeploy machine learning models on serverless GPU infrastructure with Python.