Frank
3b51b5a94a
Retire the vLLM service (frank-default-small, port 52625) on Dankclaw and serve jcbtc/Qwen3.8-27B-CIRU-ActiveFPX-PromptForge through the CIRU ROCmFPX llama.cpp runtime instead. - Build llama-server from ciru-ai/ROCmFPX tag qwen3.8-activefpx-promptforge-v2.3 (commit 103af8b41) against the private TheRock ROCm 7.15 SDK in the retired ling3-ciru venv. The model card requires ROCm 7.15 for the advertised Strix Halo performance; the system ROCm 7.2.4 selects slower kernels. CK pinned at fdf4bb7fcc984811cef48ce817d89aac064b984a; generated ck/config.h + ck/version.h copied into the CK source tree so the ggml-hip build can include them. LLAMA_BUILD_WEBUI=OFF (HF bucket llama-ui returns 404; server is consumed via the OpenAI API). - New scripts/serve-frank-small.sh + frank-default-small.env: 64K ctx, one slot, f16 KV, context checkpoints, prompt cache, native depth-4 MTP on ROCm0, PromptForge DualView sidecars (FFN + GDN), temp 0.7 top-p 0.95, reasoning off. LD_LIBRARY_PATH puts the 7.15 SDK libs before any system ROCm. - Update the systemd unit description (same service name and port). - deploy.sh: update the dankclaw target comment. - Docs: new docs/ciru-activefpx-promptforge.md with the build runbook; update docs/index.md and AGENTS.md topology. - The vLLM venvs (vllm-venv, vllm-vk-venv) were moved to /home/dank/.AGENTTRASH/ on the target; the vllm-vulkan plugin and docs were removed from the repo in an earlier commit.
3.4 KiB
3.4 KiB
vLLM Scripts — Knowledge Base
Documentation for the LLM inference fleet on two local machines (2026-08-18): llama.cpp FastMTP on Dankserver and CIRU ROCmFPX llama.cpp on Dankclaw.
Deployment Topology
graph LR
subgraph Dankserver[NVIDIA Dankserver - Ubuntu 24.04]
A[RTX 3090 24GB + 62GB RAM]
B[llama.cpp FastMTP
frank-default-large, port 7770]
C[Qwen3.8-27B-Aggressive IQ4_XS
FastMTP 32K draft + ngram-mod, 128K ctx]
A --> B --> C
end
subgraph Dankclaw[AMD Strix Halo - Ubuntu 26.04]
D[gfx1151 iGPU unified memory]
E[CIRU ROCmFPX llama.cpp
frank-default-small, port 52625]
F[jcbtc Qwen3.8-27B-CIRU-ActiveFPX-PromptForge
64K ctx, native MTP, PromptForge DualView]
D --> E --> F
end
I[LLM Clients / API] -->|HTTP :7770| B
I -->|HTTP :52625| E
Servers
| Server | GPU | VRAM / Memory | OS |
|---|---|---|---|
| Dankserver System Specs | NVIDIA RTX 3090 | 24 GB VRAM, 62 GB RAM | Ubuntu 24.04 |
| Dankclaw System Specs | AMD Radeon 8060S (Strix Halo) | gfx1151 unified memory | Ubuntu 26.04 |
Active Deployment
- deployment — deploy and update process for both servers
- frank-redo-2026-08-17 — the 2026-08-17 topology change
- ciru-activefpx-promptforge — the CIRU runtime on Dankclaw (frank-default-small)
- Dankserver — the llama.cpp FastMTP box (frank-default-large)
- Dankclaw — the CIRU ROCmFPX box (frank-default-small)
CIRU Reference (Dankclaw)
- ciru-activefpx-promptforge — model, ROCm 7.15 toolchain, build, and the frank-default-small service
vLLM Reference (historical)
- VLLM Overview — installation, CLI, API, architecture, quantization, parallelism
- VLLM Index — quick reference with commands, endpoints, and parameter table
- Running Qwen3.6 35B A3B FP8 on Dankserver — Qwen3.6-35B-A3B hardware notes and sizing (the model family formerly served by frank-default-small)
Memory Management
- RAM CPU Offloading in VLLM — KV cache swap between GPU VRAM and system RAM
- Hybrid CPU GPU Processing Dankserver — NVIDIA GPU compute with system RAM offload
- Shared Memory Architecture Dankclaw — AMD unified memory and ROCm configuration
Retired Topology (2026-08-17 redo)
- Qwen3.8 PP Deployment — the retired pipeline-parallel head + worker
- qwen3.8-spec-matrix — Qwen3.8-27B spec history (superseded by FastMTP)
- FastFlowLM NPU Inference — the retired FastFlowLM NPU endpoint
- frank-default-large-benchmark — backend/spec benchmark behind the old head
- dankserver-vram-growth — VRAM/RAM growth behind the retired cuBLAS crash
- DFlash DSpark Speculative Decoding — retired DFlash/DSpark drafting
- Quantization by Hardware Architecture — which quant format fits which GPU/CPU
Pipeline Parallelism (archive)
- Pipeline Parallelism — index of multi-node inference research. The PP pair is retired; these pages are research history.
Sibling projects
- serverAppConfigs — the Podman app
stack on the same two hosts. Its OpenWebUI consumes the
:7770endpoint on Dankserver; its Gitea instance hosts this repository.