Hermes Agent service account dda6b91330 feat(llm-inference): Day 1 playbook for RTX 3090 vLLM stack on astro-orbiter ...

- nvidia-driver-595-open (already installed 2026-08-03, idempotent)
- Python venv + vLLM 0.26.0 (already installed, idempotent)
- Gemma 2 27B model download via HuggingFace hub
- systemd vllm-serve.service on port 8000
- Hermes provider integration on carousel-of-progress
- vault_hf_token added to group_vars/all/vault
- ansible.cfg: vault_password_file set to absolute path
- inventory: astro_orbiter group added

Run with: env -u ANSIBLE_VAULT_PASSWORD_FILE ansible-playbook -i inventory.yml playbooks/day1_deploy_llm_inference.yml

2026-08-03 11:51:34 -05:00

..

~/_out

ansible vm creation (depreciated)

2025-11-21 05:48:43 -08:00

group_vars

feat(llm-inference): Day 1 playbook for RTX 3090 vLLM stack on astro-orbiter

2026-08-03 11:51:34 -05:00

host_vars

jmri: add rblundon@laptop SSH key for xpra access

2026-08-01 21:06:07 -05:00

inventory

feat: create pipeline directory structure (terraform, n8n, netbox, docs)

2026-02-25 20:51:26 -06:00

playbooks

feat(llm-inference): Day 1 playbook for RTX 3090 vLLM stack on astro-orbiter

2026-08-03 11:51:34 -05:00

roles

feat(llm-inference): Day 1 playbook for RTX 3090 vLLM stack on astro-orbiter

2026-08-03 11:51:34 -05:00

scripts

chore: archive deprecated Ansible content (OpenShift, Fastpass, FreeIPA, k8s)

2026-02-25 20:44:49 -06:00

tasks

refactor: move shared Ansible tasks to ansible/tasks/

2026-02-25 20:51:02 -06:00

templates

Move ansible to it's own directory structure

2025-07-30 12:41:18 -05:00

ansible.cfg

feat(llm-inference): Day 1 playbook for RTX 3090 vLLM stack on astro-orbiter

2026-08-03 11:51:34 -05:00

create_jarvis_user.yml

refactor: consolidate all roles into ansible/roles/ and update ansible.cfg

2026-05-26 22:22:08 -05:00

DNS_MANAGEMENT_REFACTOR.md

Sync 11-19

2025-11-19 09:36:59 -08:00

inventory.yml

feat(llm-inference): Day 1 playbook for RTX 3090 vLLM stack on astro-orbiter

2026-08-03 11:51:34 -05:00

mk

Sync 11-19

2025-11-19 09:36:59 -08:00

requirements.yml

fix(add_service_route): use FQDN for lightning-lane + add technitium collection

2026-05-30 23:43:57 -05:00