setup-modal

Deploy the CLaaS Modal serverless distillation API with DistillWorker and FastAPI.

59|6|Updated Feb 9, 2026

Search Tags:#deployment #production #serverless #api #modal #distillation

Ready to run

npx skills add https://github.com/kfallah/CLaaS --skill setup-modal

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: setup-modal
Source: https://github.com/kfallah/CLaaS/tree/main/.claude/skills/setup-modal
Command: npx skills add https://github.com/kfallah/CLaaS --skill setup-modal

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates the deployment of the CLaaS Modal serverless distillation API, essential for production environments.

Core Features & Use Cases

Production Deployment: Facilitates the deployment of the CLaaS distillation service using Modal.
Service Management: Includes a DistillWorker with a Qwen3-8B student model and a FastAPI endpoint for requests.
Use Case: Deploying the CLaaS SDPO distillation service to a production environment using Modal for scalable, remote GPU processing.

Quick Start

Invoke the setup-modal skill to deploy the Modal serverless distillation API.

Frequently Asked Questions about setup-modal

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I deploy a serverless distillation API to production using Modal?▼

To deploy a serverless distillation API to production using Modal, invoke the setup-modal skill, which manages the DistillWorker and FastAPI endpoint configuration for scalable remote GPU processing.

What is the CLaaS Modal distillation API and what does it manage?▼

The CLaaS Modal distillation API is a serverless service that manages a DistillWorker with a Qwen3-8B student model and a FastAPI endpoint for handling feedback and distillation requests in production.

Do I need to configure the Modal CLI before deploying the distillation service?▼

Yes, you need to configure the Modal CLI before deploying the distillation service, as the deployment requires it to handle initial model downloads and manage remote GPU processing infrastructure.

Can I use the Qwen3-8B model for serverless distillation with a FastAPI endpoint?▼

Yes, you can use the Qwen3-8B model as the student model for serverless distillation, managed through a FastAPI endpoint that processes feedback and distillation requests on remote GPUs.

What are the limitations or requirements for remote GPU processing with Modal?▼

Remote GPU processing with Modal requires the Modal CLI to be configured beforehand and involves initial model downloads for the Qwen3-8B student model, which may add startup overhead to the serverless deployment.