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
66 lines
2.4 KiB
Markdown
66 lines
2.4 KiB
Markdown
# 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](../vllmScripts/docs/index.md) — the deployment model this repo follows
|
|
- [[AGENTS.md]] — repository rules
|