4c438390dd2bbdc107fc6161bbfa0712890a9996
Serves jcbtc/Qwen3.8-27B-IU4-Kairic-Edge (four-artifact payload) with the qualified pinned-runner profile: 262K ctx, 1 slot, b2048/ub512, t16/tb32, f16 KV, 32 ctx checkpoints, 8 GiB prompt cache with idle-slot persistence, native MTP4, deterministic sampler, reasoning off. The serve script replicates the release pinned runner verbatim; the only differences are safe bind vars (no bare HOST env var; HIP collision rule) and this machine's split 7.15 SDK LD_LIBRARY_PATH layout. Rollback: revert this commit and redeploy; v3 model files and the v3 binary are untouched.
docs: benchmark ngram-mod stacking under MTP on v3 stack (8k/16k/64k); doc CLI order does not matter
vLLM Scripts
Deployment scripts for the LLM inference fleet (2026-08-18 topology): upstream llama.cpp on Dankserver and CIRU ROCmFPX llama.cpp 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-small | dankserver | llama.cpp (upstream b10121) | HauhauCS Qwen3.6-35B-A3B-Uncensored-Aggressive Q6_K_P + ngram-mod, 36 MoE experts on CPU, 4 slots x ~175K ctx | 7770 |
| frank-default-large | dankclaw | CIRU ROCmFPX llama.cpp (ROCm 7.15 SDK) | jcbtc Qwen3.8-27B-CIRU-ActiveFPX-PromptForge v2, native MTP + PromptForge DualView, 262K ctx / 1 slot | 52625 |
The 2026-08-17 redo retired the pipeline-parallel split (PP head + RPC
worker) and the FastFlowLM NPU endpoint. The 2026-08-18 swap retired the
vLLM service on Dankclaw and renamed the services (see AGENTS.md). 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 CIRU box.
Knowledge Base
See docs/index.md for the project knowledge base index.
Languages
Shell
60.4%
Python
21%
HTML
6.2%
Jinja
3.9%
C++
3.9%
Other
4.6%