Files
spektr a4cdd098ff
ci-static / secret-scan (push) Successful in 20s
ci-static / yamllint (push) Successful in 29s
ci-static / ansible-syntax (push) Successful in 27s
ci-static / markdown-links (push) Successful in 20s
ci-static / secret-scan (pull_request) Successful in 21s
ci-static / yamllint (pull_request) Successful in 31s
ci-static / ansible-syntax (pull_request) Successful in 29s
ci-static / markdown-links (pull_request) Successful in 20s
M6: OpenWebUI intern produktiv (Rolle open_webui, v0.13.3 digest-gepinnt) + Produktentscheidung API+WebUI, LiteLLM faellt fuer M6 weg
- llm/ansible: Rolle open_webui + playbooks/webui.yml (Production-Netz, Engine
  via llama-cpp:8080/v1, Ingress 10.0.0.90:8081, Secrets als Podman-Secrets,
  idempotent changed=0); Health/Model-Liste/Chat-Completion getestet
- gnmon_firewall: Port 8081 (OpenWebUI) nur von NPM 10.0.0.10
- CT 100: Split-DNS chat.ghostnet.selfhost.eu -> 10.0.0.10 (intern) / WAN (public)
- Doku: GNAI-000/001 — M0 entschieden (API+OpenWebUI), LiteLLM-Gate M6 = nein

Generated by Mistral Vibe.
Co-Authored-By: Mistral Vibe <vibe@mistral.ai>
2026-11-11 06:40:55 +01:00
..

LLM serving stack – Ansible control project

Executes the LLM serving stack for exactly one environment on ghostnet-ki (GNAI-008 section 7.4). Host baseline, Podman runtime, workload accounts and AMD GPU access are managed by ../../host/ansible; this project never changes host state.

Layout

  • inventories/<environment>/ – one inventory per KI environment (currently testing); deployment uses the ansible-deploy account with become: true.
  • playbooks/ai.yml – applies model_store then inference_engine.
  • roles/model_store/ – shared, pinned model weights under /var/lib/ghostnet-ai/shared/models (GNAI-010 sections 3 and 4).
  • roles/inference_engine/ – rootless Quadlets, network, image provisioning and the exclusive profile switch for llama.cpp (GNAI-010 sections 5 and 6).

Control node setup

Use the repository-wide control venv built from ../../../shared/ansible/requirements-control.txt (ansible-core==2.21.4), for example:

python3 -m venv .venv
.venv/bin/pip install -r shared/ansible/requirements-control.txt
cd llm-server/llm/ansible
../../../.venv/bin/ansible-playbook -i inventories/testing playbooks/ai.yml --syntax-check

Usage (Testing)

All commands use the operator deploy key ~/.ssh/id_ed25519_ghostnet_ai_ansible_deploy (see AGENTS.md; no ssh-agent required):

# Preview only – no changes, no downloads, no service start:
../../../.venv/bin/ansible-playbook -i inventories/testing playbooks/ai.yml \
  --check --diff --private-key ~/.ssh/id_ed25519_ghostnet_ai_ansible_deploy

# Provision model weights only (tag models):
../../../.venv/bin/ansible-playbook -i inventories/testing playbooks/ai.yml \
  --tags models --private-key ~/.ssh/id_ed25519_ghostnet_ai_ansible_deploy

# Render quadlets and start/verify the selected profile (tag service):
../../../.venv/bin/ansible-playbook -i inventories/testing playbooks/ai.yml \
  --tags service --private-key ~/.ssh/id_ed25519_ghostnet_ai_ansible_deploy

inference_engine_active_profile selects which rendered quadlet is started; all other profiles stay rendered but stopped. Check mode downloads no model and starts no service. A second identical run must report changed=0 (GNAI-010 section 10.4).

The full technical acceptance (64k/128k start, VRAM distribution, prefill ladder, restart behaviour) is an operator-run protocol documented in GNAI-010; this role automates deployment and basic health only.