homelab

Files

Hermes Agent service account 5c0df8c73c Merge origin/main — integrate monitoring/Phase3 updates with Qwen3-8B no-think deployment

Resolved add/add conflicts in:
  - defaults/main.yml: kept our version (5 original models + Qwen3-8B x2 + rows 5-6)
  - tasks/swapmode.yml: kept our version (7-model GATE 2 assert)
  - templates/llama-server-router-preset.ini.j2: kept our version (+Qwen3-8B sections)
  - templates/llama-swap-config.yaml.j2: kept our version (+chat_template_file support)

Remote changes incorporated from origin/main (14 commits):
  - Ansible Phase 3 integration (llama-swap.service.j2, tasks/monitoring.yml)
  - Prometheus monitoring: PrometheusRule, Grafana dashboard, scrape config
  - VRAM exporter script, llama-swap-phase3 cutover results
  - Day2 playbooks: nomic_embed, cpu_offload_aux, per_model_ctx, qwen38_ctx128k
  - Router: CPU-offload Coder-14B + Llama-3.1-8B
  - host_vars/astro-orbiter/vars.yml updates

2026-08-19 11:36:46 -05:00

llama-server-qwen.service.j2

feat(llm-inference): add llama.cpp router mode shadow deployment

2026-08-12 20:23:00 -05:00

llama-server-router-preset.ini.j2

Add Qwen3-8B no-think variant — dual thinking deployment (t_664289a0)

2026-08-19 11:35:08 -05:00

llama-server-router.service.j2

llm-router: CPU-offload Coder-14B + Llama-3.1-8B (t_72646029)

2026-08-17 17:06:37 -05:00

llama-swap-alerts.yml.j2

fix: correct metric names in llama-swap monitoring (llamacpp_* -> llamaswap_*), update alerts + dashboard + scrape config