Skip to main content

​
Quick Start

​
Prerequisites

  • Python 3.11+
  • uv, fast Python package manager
  • Docker (for Local and Tinker Docker deployments)
  • GPU with >= 24 GB VRAM (Local backend only)
git clone https://github.com/kfallah/CLaaS.git
cd CLaaS

​
Choose your backend

Runs SDPO training and vLLM inference on your own GPU. Requires >= 24 GB VRAM.
# Install dependencies
uv sync --extra local

# Docker setup (recommended)
cd docker
cp .env.local.example .env
# Edit .env -- set TELEGRAM_BOT_TOKEN
docker compose --profile local up --build
The first run downloads Qwen3-8B (~16 GB). Expect the vLLM health check to take 10–20 minutes on first start.

Full Local backend reference

Requirements, all config variables, services, and manual setup

​
Verify your setup

Once the stack is running, verify with: 
# Check inference endpoint
curl http://localhost:8000/v1/models -H "Authorization: Bearer sk-local"

# Check CLaaS API
curl http://localhost:8080/

# List LoRA adapters
curl http://localhost:8080/v1/lora