e20439b544
All checks were successful
Smoke Test / smoke (pull_request) Successful in 7s
- Adds ansible/ deploy_turboquant.yml playbook with per-node config - Adds turboquant-deploy role: OS-specific (darwin/debian) tasks - Adds health_check.sh and integration test (chat completion) - Adds inventory.ini.example with Mac/Allegro/Ezra groups - Deploys llama.cpp with TurboQuant (Metal on macOS) - Systemd service (Linux) with TURBO_LAYER_ADAPTIVE env
20 lines
624 B
Markdown
20 lines
624 B
Markdown
# TurboQuant Ansible Deployment
|
|
|
|
Deploy TurboQuant-compressed Gemma 4 inference across fleet nodes.
|
|
|
|
## Quick Start
|
|
|
|
```bash
|
|
# Copy and edit inventory
|
|
cp ansible/inventory.ini.example ansible/inventory.ini
|
|
|
|
# Deploy to all nodes
|
|
ansible-playbook -i ansible/inventory.ini ansible/deploy_turboquant.yml
|
|
|
|
# Run health check
|
|
ansible -i ansible/inventory.ini all -m shell -a "sudo /opt/turboquant/health_check.sh"
|
|
|
|
# Run integration test
|
|
ansible -i ansible/inventory.ini all -m shell -a "curl -s http://localhost:8081/v1/chat/completions -d '{\"model\":\"gemma-4\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello\"}]}'"
|
|
```
|