Files

T

Frank 65fbef63dc docs: what the x4 pair can and cannot do — measured, not argued

The design we sketched (trunk + KV on the 3090, MoE experts on the iGPU) is not
expressible in mainline llama.cpp. Per-tensor cross-backend placement aborts in
the scheduler -- "pre-allocated tensor (blk.0.ffn_down_exps.weight) in a buffer
(Vulkan1) that cannot run the operation (NONE)" -- and both per-layer
cross-backend forms fail at load. CUDA + Vulkan cannot serve one model; the CPU
is the only fallback side that works, which is exactly why -ot exps=CPU runs.

What the same build does instead is the surprise: iGPU-only (Vulkan/RADV, PLE in
page cache) gives 32.64 tok/s shallow, 25.77 tok/s at 64k depth and 456.7 tok/s
prefill, with the 3090 idle at 0 %. That matches halogen's deployed ~25 tok/s --
but commits 116 of the host's 121 GiB against halogen's 95.4 held with 14.7
spare, so it is not deployable beside the co-tenants. Throughput parity, memory
bankruptcy: the fleet's two-endpoint split stands, now on evidence rather than
preference.

New page LLM/x4-pair-experiment.md carries the tensor inventory, the results
table, the two scheduler limits, reproduction commands, and the traps found on
the way. Both index pages also stop calling halogen retired -- the ik swap's
stale claims were still sitting in them.

2026-09-16 17:40:37 -07:00

13 KiB

Raw Blame History

Server App Configs

Podman deployment configuration for two homelab servers: Dankserver and Dankclaw.

This repository is the single source of truth for both hosts. It tracks the container stacks and the LLM inference fleet. Edits flow through this repo, then deploy to the targets with scripts/deploy.sh (one script per target covers both workloads).

2026-08-22: the former vllmScripts repository (LLM fleet) is merged into this repo with its full git history. Its knowledge base now lives at serverAppConfigs-docs/LLM/index.md.

Hosts

Host	IP	Role	OS
Dankserver	192.168.0.235	Media & library stack	Ubuntu 24.04
Dankclaw	192.168.0.143	AI, search & development stack	Ubuntu 26.04

Stacks

Dankserver Stack — RomM, Copyparty, Calibre, Calibre-Web, Caddy
Dankclaw Stack — SearXNG (via Gluetun), ComfyUI, OpenWebUI, Hermes, Gitea, Grafana, Prometheus, Caddy

Architecture

Network Architecture — Caddy reverse proxy, hostname routing, Gluetun VPN path
Storage Policy — bind mounts, data locations, ownership
Deployment Flow — service-scoped git deploy, target map, and health checks
Testing Policy — the test seams and how to run them
E2E Suite — the Playwright suite that drives the live guard chain
Container Network Namespaces — which local services are addressable from each Podman network namespace on Dankclaw

Dankserver Storage

Entropy Volume — command-line unlock and mount helper

Dankserver Services

RomM — retro game manager
RomM-Scraping — metadata providers, cover art, naming conventions
Copyparty — file sharing and streaming
Jellyfin — media server (movies, TV, music)
Calibre — e-book library engine
Calibre-Web — e-book web frontend
ARR-Stack — automated media download overview
sonarr — TV show management
radarr — movie management
lidarr — music management
readarr — ebook/audiobook management
prowlarr — indexer management
qbittorrent — torrent download client
Plex — media server on Dankserver (lscr.io/linuxserver/plex container via quadlet; CPU decode only — no GPU passthrough)
Tautulli — Plex statistics and notifications (v2.18.1-ls242, quadlet unit)
mariadb — RomM database backend
redis — RomM cache/queue backend

Dankclaw Services

SearXNG — privacy metasearch (VPN-routed)
SearXNG Providers — unblocking Google & other upstream engines behind the VPN
Gluetun — the VPN tunnel container
Valkey — SearXNG cache and limiter store
ComfyUI — node-based AI image generation (ROCm GPU, gfx1151 build)
OpenWebUI — chat UI for local LLMs
Hermes — the Nous Research agent
Hermes-Dashboard — the Hermes web management UI (config, keys, sessions)
Hermes-WebUI — the Hermex server (loopback API for the iPhone app, SSH-tunneled)
Gitea — Git hosting (migrated)
Postgres — Gitea database backend
Seerr — unified *arr request manager (guard-chained; fronts FrankBook-Pro's stack)
Marreta — content-cleaning proxy (guard-chained; shares SearXNG's Gluetun egress)

Infrastructure

LAN-DNS — name resolution, Pi-hole, router DNS hand-off
Pi-hole — the LAN DNS server (quadlet, records, web UI)
Caddy — reverse proxy and TLS
Anubis — bot challenge proxy fronting the guarded vhosts (chain, policy, gotchas)
Authentik — the homelab's SSO / OIDC provider (forward_auth)
authentik-postgres — Authentik database service
authentik-server — Authentik server + Caddy outpost service
authentik-worker — Authentik background worker service
Homepage — password-protected service index
Homepage Design Grilling — homepage decision log and open questions
Observability — Grafana, Prometheus, Loki, Alloy, node-exporter: the stack, its quadlet deployment, its exposure, and what is still missing (alert delivery)
Grafana — dashboards (datasource and the LLM fleet dashboard provisioned as code since 2026-09-16)
Prometheus — metrics collection (5 alert rules + 1 recording rule; evaluated but not delivered — no Alertmanager)
Node-Exporter — host metrics
Loki — log storage
Alloy — log shipping (replaces Promtail)
FrankBook-Pro — Mac mini *arr + qBittorrent inside podman machine (gluetun-gated)

Research

Service Research Brief — consolidated subagent research behind these pages
ComfyUI ROCm and Vulkan — live-verified GPU path for ComfyUI on Strix Halo
Lemonade and sd.cpp — the ggml-family image-generation alternative
Llama Cpp Runtimes — mainline vs charlie12345/ROCmFPX vs ik_llama.cpp: quantization + server fit
Llama Cpp Code Diff — code-level quantization diff of the three llama.cpp runtimes
SGLang — the structured-generation serving engine (llama.cpp/vLLM comparison + our fit)
Backblaze Integration — off-site backup plan (future)
Jellyfin — media server research brief
ARR-Stack — automated download stack research brief

LLM Fleet

The LLM inference fleet on the two hosts. Full index: serverAppConfigs-docs/LLM/index.md.

Deployment and Topology

deployment — unified deploy and update process for both servers
frank-redo-2026-08-17 — the 2026-08-17 topology change
frank-medium-llamacpp-dflash2 — the ACTIVE frank-medium runbook since 2026-09-16: mainline llama.cpp (gfx1201 HIP build) serving ajgazin/Swift-Qwen3.8-27B-Uncensored-Dynamic-MTP-GGUF at UD-Q8_K_XL with the DFlash2 drafter (z-lab/Qwen3.8-27B-DFlash2-GGUF at Q8_0) on Dankserver's 2x Radeon AI PRO R9700 as one layer-split process behind the :7770 endpoint — no tensor parallelism, because the second card cannot dispatch an RCCL collective
frank-medium-radiance-mxfp4 — RETIRED 2026-09-16: the vllm-radiance MXFP4 stack serving just1moremodel/Qwen3.8-27B-Uncensored-MXFP4-awq on Dankserver's 2x Radeon AI PRO R9700 as two single-GPU replicas behind a round-robin proxy; kept as the record of the deployment frank-medium-llamacpp-dflash2 replaced, plus the PCIe-atomics evidence that rules out TP=2 on this host (since 2026-09-15/16)
Dual-R9700-Cooperation — why the two R9700s cannot run tensor-parallel together: the PCIe-atomics gate quoted from ROCclr, the measured RCCL matrix (collectives and P2P send/recv both fail on card #2, which rules out pipeline parallelism too), what is closed and what is still open, and the two hardware paths — a ~$30 M.2→PCIe x4 riser into the free, CPU-attached M.2_2 slot, or a board whose CPU x16 bifurcates to x8/x8
frank-medium-rocmfpx — PRIOR frank-medium deployment (llama.cpp era): charlie12345/ROCmFPX serving kingjones777/ Qwen3.8-27B-ROCmFPX-Q8_0-AGENT-GGUF; kept as the record of the runtime it replaced
freetoken-benchmark-sweep — KV pool vs decode speed sweep (bs1/bs3/bs4/bs6, 8k–700k KV) on the retired Dankserver RTX 3090
kingjones-strix-mtp — the Qwen3.8-27B-Q6_0 ROCmFPX AGENT era with the standalone MTP draft (Dankclaw, 2026-08-25 → 2026-08-29; historical)
agentionai-fast-imatrix — the retired frank-large runbook: agentionai/Qwen3.8-Flash-Next-ROCmFP4-FAST-imatrix (87.06 GiB, Q4_0_ROCMFP4_FAST) + own MTP draft, build-qwen38 (retired 2026-08-30; rollback record)
halogen-flash-server — the ACTIVE frank-large runbook again since 2026-09-16 (rootless Quadlet, port 7770): peonist-ai/halogen-flash-server 0.5.8 serving peonist-ai/halogen-qwen3.8-flash-next (w4b .hgn + quality overlay) on the gfx1151 iGPU — two 200k conversations over one 400,384-position pool, deployed flags, memory model, client contract
frank-large-ik-uncensored — the RETIRED 2026-09-16 frank-large runbook and rollback target (2026-09-15 → 09-16): ik_llama.cpp serving mradermacher/Qwen3.8-Flash-Next-Uncensored-i1-Q4_K_M on the RTX 3090 + Strix Halo hybrid — its measured envelope is why the fleet went back
dankclaw-iommu-translation-off — why Dankclaw boots with amd_iommu=off since 2026-09-11 (13-16 % prefill), what it cost (the NPU endpoint), and how to revert
kingjones-strix-rocmfp4 — the PRIOR frank-large runbook (2026-08-30 → 2026-09-11) and the rollback target: kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF on the card's pinned kingjones30/ROCmFPX build
kingjones-q8agent-rocmfpx — the retired Q8_0-AGENT investigation and set_rows failure
eemin-rocmi4-mtp — the former caf-eemin Qwen3.8-27B ROCmI4 embedded-MTP model on Dankclaw
ciru-activefpx-promptforge — the RETIRED v3 CIRU PromptForge runtime on Dankclaw (superseded 2026-08-24)
kingjones-strix-mtp — the kingjones Qwen3.8-27B ROCmFP4 STRIX MTP model on Dankclaw (active)
dealign-ornith-crack — the retired Ornith-1.5-35B-A3B CRACK model on Dankserver (retired 2026-09-02)
frank-small-qwen38-gsq-rco — the ACTIVE frank-small runbook since 2026-09-16: mainline llama.cpp serving ISTA-DASLab/Qwen3.8-27B-GSQ-RCO- GGUF at IQ3_S (own MTP head + BF16 vision projector) on Dankclaw's RTX 3090, port 7771 — the 3090 freed when halogen took the iGPU back for frank-large
ikllama-ornith-dankserver — the retired ik_llama.cpp runtime for the old frank-small (q8_0 + Hadamard KV cache, split-mode none; 2026-08-26)
freetoken-frank-small — RETIRED 2026-09-15: the FreeToken/CUDA frank-small runbook, retired with the RTX 3090
kairic-edge — the retired Kairic Edge IU4 experiment (2026-08-22)
dflash2-large-vulkan — the retired DFlash2 Vulkan deployment (2026-08-21)
Dankserver System Specs — the 2x R9700 box hardware (frank-medium)
Dankclaw System Specs — the Strix Halo gfx1151 box (frank-large)
Dankclaw Improvements — host-level changes on the Strix Halo box
Swap Configuration — the 64 GiB /swap.img host swapfile (raised from 8 GiB 2026-09-12): fstab-driven swap.img.swap unit, the safe resize ordering that drains the old file into fresh swap instead of into a host whose MemAvailable lies by the size of the model, and the swappiness caveat
frank-npu — the RETIRED FLM NPU endpoint on Dankclaw (2026-09-11): Gemma4 E4B vision+audio pack on the XDNA2 NPU, port 7771; kept as the retirement record, including the IOMMU/SVA err=-19 root cause and where every dependent route moved

Benchmarks and Sizing

frank-large-benchmark — backend/spec benchmark behind the old head
ubatch-benchmark-large — active-model llama-bench ubatch sweep plan and results
frank-small-benchmark — the small-model benchmark suite
Running Qwen3.6 35B A3B FP8 on Dankserver — Qwen3.6-35B-A3B hardware notes
Running Qwen3.6 27B FP8 on Dankclaw — Qwen3.6-27B sizing on the iGPU
qwen3.8-strix-optimizations — Strix Halo tuning notes
x4-pair-experiment — what a 3090 + Strix Halo combination can and cannot do in mainline llama.cpp (measured 2026-09-16): the tensor inventory that decides a split, the scheduler limits that kill a cross-backend one, and the iGPU-only result that matches halogen's decode rate while leaving the 3090 idle — for 116 of the host's 121 GiB

Memory and Hardware

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
dankserver-vram-growth — VRAM/RAM growth behind the retired cuBLAS crash
Quantization by Hardware Architecture — which quant format fits which GPU/CPU

Retired Topology and History

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
DFlash DSpark Speculative Decoding — retired DFlash/DSpark drafting
ling-3.0-flash-trial — the Ling-3.0-Flash trial runbook
ling-3.0-flash-vllm-plan — the Ling-3.0-Flash vLLM plan (retired)

vLLM Reference (historical)

VLLM Overview — installation, CLI, API, architecture, quantization, parallelism
VLLM Index — quick reference with commands, endpoints, and parameter table
vllm_research_findings — research findings from the vLLM era

Pipeline Parallelism (archive)

Ethernet Bandwidth Math — the bandwidth budget for the PP pair
Expected Performance — expected PP throughput
llama.cpp RPC — the RPC transport between head and worker
Mixed-Vendor Experiments — cross-vendor PP experiments
Qwen3.6 27B Spec Methods — spec-decoding methods for the 27B
Sample Script Set — reference scripts for the PP pair
vLLM Pipeline Parallelism — vLLM's PP implementation

Update Log

log — chronological record of knowledge-base changes

13 KiB Raw Blame History Unescape Escape