Frank
1e9d921b95
Live-verified on Dankclaw 2026-08-14: - official rocm/comfyui image is built PYTORCH_ROCM_ARCH=gfx942;gfx950 (datacenter only) -> torch.cuda.is_available() False on gfx1151 - AMD gfx1151-tagged PyTorch build (rocm/vllm:...gfx1151...pytorch_2.9.1) -> avail True, Radeon 8060S, cap (11,5); needs /dev/kfd + /dev/dri - torch.backends.vulkan is compiled out of standard wheels; no ComfyUI --vulkan flag exists; Vulkan is a dead end for ComfyUI - Lemonade Server does image gen via wrapped stable-diffusion.cpp, whose HIP kernels include gfx1151 -> works where ComfyUI's torch cannot New pages: ComfyUI ROCm and Vulkan, Lemonade and sd.cpp; ComfyUI.md qualified; compose stays --cpu until a gfx1151-enabled torch image is built
2.4 KiB
2.4 KiB
Server App Configs
Podman deployment configuration for two homelab servers: Dankserver and Dankclaw.
This repository tracks the container stacks for both hosts. Git is the single source of truth. Edits flow through this repo, then deploy to the targets with scripts/deploy.sh. This mirrors the workflow of the vllmScripts repository.
Hosts
| Host | IP | Role | OS |
|---|---|---|---|
| Dankserver | 192.168.0.235 | Media & library stack | Ubuntu 24.04 |
| Dankclaw | 192.168.0.143 | AI, search & development stack | Ubuntu 26.04 |
Stacks
- Dankserver Stack — RomM, Copyparty, Calibre, Calibre-Web, Caddy
- Dankclaw Stack — SearXNG (via Gluetun), ComfyUI, OpenWebUI, Hermes, Gitea, Grafana, Prometheus, Caddy
Architecture
- Network Architecture — Caddy reverse proxy, hostname routing, Gluetun VPN path
- Storage Policy — bind mounts, data locations, ownership
- Deployment Flow — git-based deploy, target map, health checks
- Testing Policy — the test seams and how to run them
Dankserver Services
- RomM — retro game manager
- Copyparty — file sharing and streaming
- Calibre — e-book library engine
- Calibre-Web — e-book web frontend
Dankclaw Services
- SearXNG — privacy metasearch (VPN-routed)
- Gluetun — the VPN tunnel container
- Valkey — SearXNG cache and limiter store
- ComfyUI — node-based AI image generation (CPU)
- OpenWebUI — chat UI for local LLMs
- Hermes — the Nous Research agent
- Gitea — Git hosting (migrated)
- Postgres — Gitea database backend
Infrastructure
- Caddy — reverse proxy and TLS
- Homepage — password-protected service index
- Observability — Grafana, Prometheus, Loki, Alloy
- Grafana — dashboards
- Prometheus — metrics collection
- Node-Exporter — host metrics
- Loki — log storage
- Alloy — log shipping (replaces Promtail)
Research
- Service Research Brief — consolidated subagent research behind these pages
- ComfyUI ROCm and Vulkan — live-verified GPU path for ComfyUI on Strix Halo
- Lemonade and sd.cpp — the ggml-family image-generation alternative
- Backblaze Integration — off-site backup plan (future)
See Also
- vllmScripts repository — the deployment model this repo follows
- AGENTS.md — repository rules