From 2b115ad378fd438e70f33b607e118abeb4c31249 Mon Sep 17 00:00:00 2001 From: Frank Date: Sat, 22 Aug 2026 15:49:44 -0700 Subject: [PATCH] README + .gitignore: one repo, two workloads README: merged service table (stack + LLM), structure incl. old/ and docs/LLM/, unified deploy note, merge note. .gitignore: merged both files; !scripts/*.env exception for the LLM tunables (paths and numbers, never credentials); .obsidian/, __pycache__/, .venv/ from the vllmScripts side. --- .gitignore | 12 ++++++++++++ README.md | 43 ++++++++++++++++++++++++++----------------- 2 files changed, 38 insertions(+), 17 deletions(-) diff --git a/.gitignore b/.gitignore index cd47e29..1bffaf6 100644 --- a/.gitignore +++ b/.gitignore @@ -2,6 +2,8 @@ .env *.env !.env.example +# LLM fleet tunables (paths and numbers, never credentials) +!scripts/*.env # pi subagent artifacts .pi-subagents/ @@ -9,6 +11,16 @@ # Agent trash .AGENTTRASH/ +# Python +__pycache__/ +*.pyc + +# Virtual environments +.venv/ + +# Obsidian editor state +.obsidian/ + # Editor/OS noise *.swp .DS_Store diff --git a/README.md b/README.md index f927b22..1db7cdc 100644 --- a/README.md +++ b/README.md @@ -1,13 +1,19 @@ # Server App Configs -Podman deployment configuration for two homelab servers: Dankserver and Dankclaw. +The single repository for the two homelab servers: the Podman container +stacks **and** the LLM inference fleet. One repo, one checkout per host, +one deploy script. + +> 2026-08-22: the former `vllmScripts` repository (LLM fleet) is merged +> into this repo with its full git history. See AGENTS.md for the merge +> note. ## Targets -| Host | User | IP | Stack | -|------|------|----|-------| -| dankclaw | dank | 192.168.0.143 | AI, search, development, observability | -| dankserver | dank | 192.168.0.235 | media and library | +| Host | User | IP | Podman stack | LLM service | LLM port | +|------|------|----|--------------|-------------|----------| +| dankserver | dank | 192.168.0.235 | media and library | frank-default-small (llama.cpp, Qwen3.6-35B-A3B) | 7770 | +| dankclaw | dank | 192.168.0.143 | AI, search, development, observability | frank-default-large (CIRU ROCmFPX, Qwen3.8-27B) | 52625 | ## Active Services @@ -16,6 +22,7 @@ Podman deployment configuration for two homelab servers: Dankserver and Dankclaw | RomM | dankserver | romm.dankserver.local | 8085 | | Copyparty | dankserver | files.dankserver.local | 3923 | | Calibre-Web | dankserver | books.dankserver.local | 8083 | +| frank-default-small | dankserver | — (bare endpoint) | 7770 | | SearXNG | dankclaw | search.dankclaw.local | 8081 | | ComfyUI | dankclaw | comfyui.dankclaw.local | 8188 | | OpenWebUI | dankclaw | chat.dankclaw.local | 3000 | @@ -23,31 +30,33 @@ Podman deployment configuration for two homelab servers: Dankserver and Dankclaw | Gitea | dankclaw | gitea.dankclaw.local | 3001 | | Grafana | dankclaw | grafana.dankclaw.local | 3002 | | Prometheus | dankclaw | prometheus.dankclaw.local | 9090 | +| frank-default-large | dankclaw | — (bare endpoint) | 52625 | ## Structure - `dankserver/` — compose.yaml + Caddyfile + .env.example for the Dankserver stack - `dankclaw/` — compose.yaml + Caddyfile + .env.example for the Dankclaw stack - `shared/` — homepage, prometheus config, deploy helpers -- `scripts/` — deploy.sh and stack control scripts -- `docs/` — project knowledge base (Obsidian vault, wikilinks) +- `scripts/` — `deploy.sh` (unified: stack + LLM), LLM serve scripts, systemd units, env tunables, bench harnesses +- `old/` — retired PP/NPU-era LLM scripts (reference only) +- `docs/` — project knowledge base (Obsidian vault, wikilinks). `docs/LLM/` is the LLM fleet - `tests/` — bats test suite (see [[Testing Policy]]) ## Deployment -See [docs/Architecture/Deployment Flow.md](docs/Architecture/Deployment Flow.md). Run `./scripts/deploy.sh ` after pushing committed changes. +See [docs/Architecture/Deployment Flow.md](docs/Architecture/Deployment%20Flow.md) +and [docs/LLM/deployment.md](docs/LLM/deployment.md). Run +`./scripts/deploy.sh ` after pushing committed changes. +It pushes, pulls on the target, restarts the podman stack and the LLM +service, and checks both health endpoints. ## Knowledge Base -The `docs/` directory is an Obsidian vault. Start at [docs/index.md](docs/index.md). +The `docs/` directory is an Obsidian vault. Start at +[docs/index.md](docs/index.md). The LLM fleet knowledge base lives at +[docs/LLM/index.md](docs/LLM/index.md). ## Testing -Run `./tests/run.sh` before every push. See [docs/Architecture/Testing Policy.md](docs/Architecture/Testing Policy.md). - -## Also See - -- [vllmScripts](http://dankclaw:3000/dank/vllmScripts) (local: `../vllmScripts`) — - the model-serving scripts this stack consumes: `frank-default-large` - (llama.cpp PP head, `:7770`, backend of OpenWebUI) and - `frank-default-small` (FastFlowLM NPU, `:52625`) +Run `./tests/run.sh` before every push. See +[docs/Architecture/Testing Policy.md](docs/Architecture/Testing%20Policy.md).