Frank
2e1a78aeb4
- CTX_SIZE 65536 -> 131072 (user request). KV at 128K is 8 GiB (64 KiB/token f16); estimated ~43 GiB used of the 64 GiB SVM pool, ~21 GiB headroom. - REASONING off -> on with REASONING_FORMAT=deepseek, so <think> reasoning lands in message.reasoning_content (OpenAI-compatible) instead of being left unparsed in content.
vLLM Scripts
Deployment scripts for the LLM inference fleet (2026-08-17 topology): llama.cpp FastMTP on Dankserver and vLLM ROCm on Dankclaw.
Targets
| Host | User | Codename | GPU |
|---|---|---|---|
| dankserver | dank | Dankserver | NVIDIA RTX 3090 24 GB + 62 GB RAM |
| dankclaw | dank | Dankclaw | AMD Strix Halo iGPU gfx1151 (unified memory) |
Active Services
| Service | Host | Runtime | Model | Port |
|---|---|---|---|---|
| frank-default-large | dankserver | llama.cpp (patched FastMTP build) | HauhauCS Qwen3.8-27B-Uncensored-Aggressive IQ4_XS, FastMTP 32K draft + ngram-mod, K q8_0 / V f16 KV, 128K ctx | 7770 |
| frank-default-small | dankclaw | vLLM ROCm (vllm-venv) | nameistoken Qwen3.6-35B-A3B Quark W8A8 INT8, full 262144 ctx, no KV quantization, 4 seqs, batch 8192, ngram spec + tool calling | 52625 |
The 2026-08-17 redo retired the pipeline-parallel split (PP head + RPC
worker) and the FastFlowLM NPU endpoint. Their scripts are preserved in
old/scripts/ for reference.
Structure
docs/— knowledge base: deployment runbook, model notes, research archivescripts/— serve scripts, env files, systemd units, deploy and test toolsold/scripts/— retired PP/NPU-era scripts (reference only)
Deployment
See docs/deployment.md. Run
FRANK_SUDO_PW=... ./scripts/deploy.sh dankserver for the llama.cpp box or
FRANK_SUDO_PW=... ./scripts/deploy.sh dankclaw for the vLLM box.
Knowledge Base
See docs/index.md for the project knowledge base index.