Frank
6efb0fb231
Replace the llama.cpp Tiel-Coder-35B-A3B (UD-Q6_K_XL) deployment with FreeToken v0.1.2 — an edge-native MoE serving engine that keeps expert weights in host RAM with an LRU GPU cache and paged KV with radix prefix sharing. Model: Qwen/Qwen3.6-35B-A3B-FP8 (modelopt block-fp8, 128×128 weight_block_size). Architecture: qwen3_5_moe — 40 layers (10 attention + 30 GDN), 256 experts/8 used. Production config: - 2048 MoE cache slots (20% of 10240 expert instances, ~6.0 GiB VRAM) - 453005 KV tokens (~8.6 GiB, ~20 KiB/token for 10 attn layers) - 4 max-running-requests (mamba slot pool: 24 slots) - bs4 decode: ~87 tok/s aggregate, ~30 tok/s bs1 - Prefill: ~1,130 tok/s at 4k prompt Quirk: FreeToken v0.1.2 supports modelopt block-fp8, NVFP4, and per-tensor FP8, but NOT compressed-tensors per-channel FP8 (Huihui/Ornith both failed). Live KV resize via ft ctl cache grows KV by shrinking MoE; reverse needs restart. Old llama.cpp scripts archived to .AGENTTRASH/. Full benchmark sweep (bs1/bs3/bs4/bs6, 8k–700k KV) documented in docs/LLM/freetoken-benchmark-sweep.md.
Server App Configs
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
vllmScriptsrepository (LLM fleet) is merged into this repo with its full git history. See AGENTS.md for the merge note.
Targets
| 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) | 7770 |
Active Services
| Service | Host | Hostname | Port |
|---|---|---|---|
| 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 |
| Hermes | dankclaw | hermes.dankclaw.local | 8090 |
| Gitea | dankclaw | gitea.dankclaw.local | 3001 |
| Grafana | dankclaw | grafana.dankclaw.local | 3002 |
| Prometheus | dankclaw | prometheus.dankclaw.local | 9090 |
| frank-default-large | dankclaw | — (bare endpoint) | 7770 |
Structure
dankserver/— compose.yaml + Caddyfile + .env.example for the Dankserver stackdankclaw/— compose.yaml + Caddyfile + .env.example for the Dankclaw stackshared/— homepage, prometheus config, deploy helpersscripts/—deploy.shanddeploy-remote.sh(service-scoped deployment), the planner, LLM serve scripts, systemd units, env tunables, and bench harnessesold/— retired PP/NPU-era LLM scripts (reference only)docs/— project knowledge base (Obsidian vault, wikilinks).docs/LLM/is the LLM fleettests/— bats test suite (see Testing Policy)
Deployment
See docs/Architecture/Deployment Flow.md
and docs/LLM/deployment.md. Run
./scripts/deploy.sh <dankclaw|dankserver> after committing changes. It
plans and deploys only the changed services. Use --service NAME for an
explicit single-service retry; inference is restarted only when its own files
(or the shared chat template) changed.
Knowledge Base
The docs/ directory is an Obsidian vault. Start at
docs/index.md. The LLM fleet knowledge base lives at
docs/LLM/index.md.
Testing
Run ./tests/run.sh before every push. See
docs/Architecture/Testing Policy.md.