Your Name c29e24b51b litellm: route all homelab LLM load to Anvil/Ollama by default ...

Per-model api_base/api_key overrides in the template (default stays
Meridian's local port). All standard aliases (claude-*, gpt-*) now point
at Anvil's Ollama (mini/haiku-class -> llama3.1:8b, rest -> llama3.3:70b).
Claude/Max reachable only via new *-max escape-hatch aliases.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-05-28 11:16:46 -04:00

..

litellm-config.yaml.j2

litellm: route all homelab LLM load to Anvil/Ollama by default

2026-05-28 11:16:46 -04:00

litellm.env.j2

litellm: add OpenAI→Meridian shim role (venv + systemd, port 4000)

2026-05-19 11:23:52 -04:00

litellm.service.j2

litellm: add OpenAI→Meridian shim role (venv + systemd, port 4000)

2026-05-19 11:23:52 -04:00