vh
e376d0aec9
Captures the full workspace state built up to this point:
- CLAUDE.md + README.md describing conventions and the four-host fleet
(ana-ml2, ana-docker, nh3-docker, esh-docker-vm).
- Per-host notes under servers/<host>/ with ssh-target fallback files
and latest system-details snapshots (two in-compose credential leaks
scrubbed; the upstream compose files still need to move those to .env).
- scripts/: server_inspect.sh (read-only remote diagnostic),
refresh-server-info.sh (dir-driven discovery + snapshot capture with
validation warnings), add-host.sh, sync-stacks.sh (pull
compose/conf trees), deploy-stack.sh (push with per-file diff + prompt).
- stacks/: canonical compose for backrest, beszel, dozzle, llama-swap,
rest-server-ana, rest-server-nh3, vllm-qwen3, plus the retired
infinity reference. All use the .env-driven + traefik-net + homepage
label pattern.
- configs/restic/ana-docker/: first resticprofile config + pre-backup
hook (Synapse pg_dump, Seafile mysqldump, Vaultwarden SQLite); templates
for the other three hosts to come.
- docs/pfi/: general infrastructure reference carried over.
- .gitignore excludes .env, stacks-mirror/, and assorted secret/state
filenames to prevent re-leaks on later commits.
51 lines
1.6 KiB
YAML
51 lines
1.6 KiB
YAML
# llama-swap — GGUF model server with on-demand model swapping.
|
|
#
|
|
# Proxies OpenAI-compatible API requests to llama.cpp server instances
|
|
# and swaps which model is loaded into VRAM per request. Runs on
|
|
# ana-ml2 using both GPUs dynamically (no explicit device pinning —
|
|
# llama-swap picks per-model-definition).
|
|
#
|
|
# Model definitions live in /opt/docker/conf/llama-swap/config.yaml on
|
|
# the server. Canonical copy of that config is config.yaml in this
|
|
# workspace; deploy with scp + `docker compose restart` or the script
|
|
# at the bottom of README.md.
|
|
#
|
|
# All tunables live in .env — edit that, not this file.
|
|
|
|
services:
|
|
llama-swap:
|
|
image: ghcr.io/mostlygeek/llama-swap:${LLAMA_SWAP_VERSION}
|
|
container_name: llama-swap
|
|
restart: unless-stopped
|
|
stdin_open: true
|
|
tty: true
|
|
runtime: nvidia
|
|
ports:
|
|
- "${LLAMA_SWAP_PORT}:8080"
|
|
volumes:
|
|
- /opt/docker/conf/llama-swap/config.yaml:/app/config.yaml
|
|
- ${MODELS_DIR}:/models
|
|
- ${HF_CACHE_DIR}:/hfcache
|
|
environment:
|
|
- HF_HOME=/hfcache
|
|
- HF_HUB_CACHE=/hfcache/hub
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "curl -fsS http://localhost:8080/ >/dev/null || exit 1"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 30s
|
|
networks:
|
|
- tnet
|
|
labels:
|
|
- homepage.group=AI Systems
|
|
- homepage.name=llama-swap
|
|
- homepage.icon=mdi-swap-horizontal
|
|
- homepage.description=GGUF model swapper (llama.cpp; ana-ml2)
|
|
- homepage.href=http://10.250.50.54:${LLAMA_SWAP_PORT}
|
|
|
|
networks:
|
|
tnet:
|
|
name: traefik-net
|
|
external: true
|