# llm stack — model-swapping LLM backend for the Hermes agent.
#
# llama-swap fronts multiple GGUF models on the single Tesla P100 (16GB). Only one
# model fits in VRAM at a time, so llama-swap presents all of them via /v1/models
# and hot-swaps on demand (selecting a different model = a few-second reload). The
# per-model llama-server commands + args live in llama-swap-config.yaml.
#
# The bundled llama.cpp in llama-swap:cuda is build 9803 (5c7c22c3e) — the same
# build validated on this Pascal card for gemma4 + gpt-oss. Default model and the
# selectable menu are driven from Hermes (~/.hermes/config.yaml: model.default =
# gpt-oss-20b; provider valhalla-p100 models: list = the keys in the swap config).
#
# Endpoint published on 172.20.0.1:8090 (edge bridge gateway, a host IP) for the
# host-side Hermes agent. Internal-only; no Caddy, no auth (LAN/host-only).
# Image is infra-pinned out of Watchtower.
services:
  llama-swap:
    image: ghcr.io/mostlygeek/llama-swap:cuda
    container_name: llama-swap
    restart: unless-stopped
    labels:
      - "com.centurylabs.watchtower.enable=false"
    networks: [llm]
    devices:
      - "nvidia.com/gpu=0"
    volumes:
      - /storage1/labdata/llm/models:/models
      - ./llama-swap-config.yaml:/app/config.yaml:ro
    ports:
      - "172.20.0.1:8090:8080"
    healthcheck:
      test: ["CMD", "curl", "-fsS", "http://localhost:8080/health"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s

networks:
  llm:
    name: llm
    driver: bridge