# LLM Fleet — Knowledge Base

**Dankserver runs the radiance engine (StillDeadcode) on frank-primary**
(digest-pinned `stilldeadcode/radiance` image, engine as entrypoint,
driving `podman run` directly, root systemd unit, :7770): the OFFICIAL
`Qwen/Qwen3.8-Flash-Next-FP8` checkpoint at NATIVE block-FP8 precision
(converted no-recipe to `qwen4exp-fp8-native.rad` — see the runbook for
the descriptor-staging law), on BOTH R9700s TP=2 (`--tp-wire wht6`),
experts in a 40 GiB/rank pinned host pool + VRAM cache (ratio 0.82), the
47.7 GiB PLE table pinned to host RAM, fp8 KV, MTP spec decode depth 3,
2 × 200,000 first boot. Rollback tags frank-primary-freetoken-pr587-20261005
and frank-primary-vllm-shapeG-20261003),
and Dankclaw runs two endpoints — **halogen-flash-server 0.16.2
(frank-large, port 7770: ghcr.io/peonist-ai/halogen-flash-server @ pinned
digest serving the Quat3rnion ABLITERATED Swift1.5 finetune of
Qwen3.8-Flash-Next v2, a ~62 GiB v2 .hgn that loads in no other engine,
MTP spec decode always-on (HALOGEN_SPEC_ADAPT=0), TWO slots at 200,192
ctx, vision ON)** and
**llama.cpp CUDA (frank-secondary, port 7771: HauhauCS Gemma4-26B-A4B QAT
Uncensored Q4_K_M GGUF — 26B MoE hybrid (25 sliding-window + 5 full-attention
layers), ONE 200,704-token conversation, MTP disabled,
q8_0 K + q8_0 V (FP8 class), vision via the publisher's own BF16
mmproj, on the RTX 3090)**.

> 2026-08-22: the former `vllmScripts` repository is merged into the
> serverAppConfigs repository. This knowledge base moved from the old repo's
> `serverAppConfigs-docs/` root to `serverAppConfigs-docs/LLM/`. The fleet scripts and units now live in the
> repo's `scripts/` directory.

## Deployment Topology

```mermaid
graph LR
    subgraph Dankserver[AMD Dankserver - Ubuntu 26.04]
        A[2x Radeon AI PRO R9700
gfx1201, 32 GiB each]
        B2[radiance StillDeadcode, digest-pinned image
podman run, frank-primary, port 7770]
        C[Qwen3.8-Flash-Next FP8 OFFICIAL, native block-FP8
2x R9700 TP=2 wht6, experts 40 GiB/rank pinned pool + VRAM,
PLE 47.7 GiB pinned RAM, fp8 KV 7.32 KiB/tok, MTP depth 3,
2 x 200000, froggeric v22.5]
    end

    subgraph Dankclaw[AMD Strix Halo - Ubuntu 26.04]
        E2[RTX 3090 (PCIe x4 dock) +
gfx1151 iGPU 114 GiB GTT]
        E[flash-server container gfx1151, digest-pinned image
frank-large, port 7770]
        F[flash-server v2 abliterated Swift1.5 .hgn + ngram table + vision tower
2 x 200192 ctx, MTP always-on, image input]
        G[llama.cpp master CUDA sm_86
frank-secondary, port 7771]
        H[Gemma4-26B-A4B QAT Uncensored Q4_K_M GGUF
1 x 200704 ctx, q8_0 K + q8_0 V, MTP off, mmproj vision]
        E2 --> E --> F
        E2 --> G --> H
    end

    CLI[LLM Clients / API] -->|HTTP :7770| B2
    CLI -->|HTTP :7770| E
    CLI -->|HTTP :7771| G
```

## Servers

| Server                                  | GPU                           | VRAM / Memory        | OS           |
| --------------------------------------- | ----------------------------- | -------------------- | ------------ |
| [[Dankserver System Specs\|Dankserver]] | 2x AMD Radeon AI PRO R9700 | 2x 32 GB VRAM, 246 GB RAM | Ubuntu 26.04 |
| [[Dankclaw System Specs\|Dankclaw]]     | AMD Radeon 8060S (Strix Halo) | gfx1151 unified memory | Ubuntu 26.04 |

## Active Deployment

- [[frank-large-flash-server-v2-swift15]] — **ACTIVE since 2026-10-06**
  (root systemd unit + podman, port 7770): the digest-pinned
  `ghcr.io/peonist-ai/halogen-flash-server` 0.16.2 engine serving the
  Quat3rnion ABLITERATED Swift1.5 finetune of peonist's
  Qwen3.8-Flash-Next v2 checkpoint (`qwen38-flash-next-v2-swift15-abliterated.hgn`,
  66.7 GB compacted r2 of the card's 89.8 GB append-only original,
  sha256-verified) with the REQUIRED n-gram lookup table (51.2 GB,
  @peonist 5cc17cea) and the vision tower (897.9 MB, @e053f488) beside
  it. TWO slots of 200,192 ctx, MTP head ALWAYS ON (`HALOGEN_SPEC_ADAPT=0`
  — the adaptive default turns the head off per request and halves
  decode), server-side sampler at the card's 1.0/0.95/20, coupled
  cap/timeout 65536/7200, prompt cache ON by default (the 27B engine's
  manual `HALOGEN_CACHE_MB` pin era is over — warm 100k turn ≈ 2 s vs
  ≈ 88 s cold). Vision ON (image_url parts only). Card: 53-57 t/s
  greedy, ~1,640 t/s prefill at 34k, ~72 % fewer thinking tokens.
  Rollback: revert the swap commit; the 27B payload + fetch script stay
  on disk
- [[frank-large-halogen27b-dflash2]] — **RETIRED 2026-10-05 → 10-06
  (rollback target; payload + fetch script + image on disk)**: the
  digest-pinned `ghcr.io/peonist-ai/halogen` 0.1.4 engine serving
  `peonist-ai/halogen-qwen3.8-27b` (`qwen3.8-27b-p1w4d-d2.hgn`, 33.4 GiB)
  — DFlash2 drafter, ONE 200,700 slot, text-only (the engine ignored the
  vision encoder), censored base. Owns the measured lessons: the prompt
  cache pin (`HALOGEN_CACHE_MB=16384` — auto was OFF at the 36.9 GB
  two-entry floor; a 17.3k cold prefill of 27.0 s resumed in 1.7 s warm),
  the FA tile rejection (`HALOGEN_FA_TQ=256`: prefill −9.5 %, decode
  ±0.3 %), and deep decode at 3.3-3.8 t/s@80k being structural. The
  foreground-`podman run` ledger capture and the deep-role rerouting
  (`slow`/`advisor` → frank-primary) carried forward. Superseded by the
  MODEL swap: the abliterated v2 .hgn loads only in flash-server, so the
  engine moved with the model
- [[frank-secondary-llama-qwen35-9b-q6k-2x200704]] — **ACTIVE since 2026-10-07**
  (root systemd unit, port 7771): llama.cpp master (CUDA sm_86) serving
  HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive **Q6_K** on the RTX 3090
  — TWO 200,704-token conversations (`--ctx-size 401408 --parallel 2`), exact
  f16 K + f16 V, vision via the publisher's BF16 mmproj. MTP is OFF because
  the file has no MTP tensors at all. Priced from the MiMo Q6_K boots (same
  qwen35 geometry, same card, same shape). Supersedes the Gemma4 era (below).
- [[frank-secondary-llama-gemma4-q4km-200704]] — **RETIRED 2026-10-07** (same
  day; superseded by qwen35-9b-q6k; payload on disk as rollback): llama.cpp
  master (CUDA sm_86) serving HauhauCS/Gemma4-26B-A4B-QAT-Uncensored-
  HauhauCS-Balanced-MTP **Q4_K_M** on the RTX 3090 — ONE 200,704-token
  conversation, f16 K + q8_0 V, vision via the publisher's mmproj. MTP was
  OFF (the gemma4-assistant drafter costs ~1.9 GiB: 23,806 used/319 free with
  it, 21,890/2,235 without).
- [[frank-secondary-llama-swift15-unc-iq3xxs-mtp-114688]] — **RETIRED
  2026-10-07** (superseded by gemma4-q4km; payload on disk as rollback);
  ACTIVE 2026-10-05 (evening) → 2026-10-07; UNCECERSED RCO-IQ3_XXS with
  MTP back on since
  2026-10-06 evening; RENAMED from frank-small and reshaped to 2 ×
  114,688 / ubatch ladder 512 → 1024 → **2048** late 2026-10-06** (root
  systemd unit, port
  7771): llama.cpp master
  (CUDA sm_86) serving ajgazin/Swift-1.5-Qwen3.8-27B-Uncensored-Dynamic-MTP-
  GGUF **RCO-IQ3_XXS-mtp** (27B; the MTP head in the file is DRAFTED —
  draft-mtp depth 3, ngram skipped on the recurrent-rollback law) on the
  RTX 3090, TWO 114,688-token conversations at Frank's 112k cap (pool
  229376 / parallel 2 — cut from 131,072 to fund the ubatch rungs;
  **1,005 MiB free at boot, 763 settled after a vision probe**) with
  q8_0 K + q8_0 V (FP8 class, 34 KiB/token vs 64 at f16) and
  vision through the publisher's own mmproj-BF16.gguf. Prefill 1,209
  t/s @ 3,760; decode ~52–58 t/s recipe (ubatch-invariant; acceptance
  noise 34–54 %).
  RCO-IQ3_XXS tier is a per-tensor allocation mix of stock types; the
  payload is the UNCECERSED Swift 1.5 (23/100 refusals vs Swift 1.5's
  98/100). Replaces BOTH same-day payloads: the live MiMo Q6_K shape
  (below) and the Ornith-1.5-9B Q8_0 swap that was committed
  (77decb5..380aafa) but never deployed
- [[frank-secondary-llama-mimo-q6k-2x200704]] — **RETIRED 2026-10-05 (evening;
  rollback target; payload on disk)**: llama.cpp master (CUDA sm_86)
  serving bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF **Q6_K**, TWO slots of
  200,704 with FULLY UNQUANTIZED KV (f16 K + f16 V) and the mmproj for
  vision — 94.4 tok/s decode (the rung costs a measured -10 % vs Q5_K_M:
  weight-bandwidth-bound), batch 4096 / ubatch 2048 since 2026-10-05
  (+4.6 % prefill, measured), 2,279 MiB of the card left free. This was
  the LIVE payload when Swift cut over. The ubatch A/B table and the
  probe-size trap (>=256 px images or the model says "video") live inside
- [[frank-secondary-llama-mimo-q5km]] — **RETIRED 2026-10-02 → 10-03 (rollback
  target; payload on disk; owns the measured boot-pair table)**: the same
  runtime and the same 2 x 200,704 + f16 KV shape one quant rung lower —
  104.8 tok/s, 3,571 MiB true free
- [[frank-primary-radiance-swift15-w4dn8]] — **STAGED (campaign running)**:
  Swift1.5 Qwen3.8-Flash-Next BF16 → GPTQ-calibrated W4Dn8 `.rad` on radiance
  1.0.13 (recipe + 10M-token calibration + KLD gate vs the BF16 container);
  replaces the FP8-native payload when the gates pass
- [[frank-primary-radiance-qwen38-native-fp8]] — **ACTIVE since 2026-10-05**
  (root systemd unit, port 7770): the StillDeadcode **radiance** engine
  (C++/HIP, libr4d gfx1201 kernels, digest-pinned 287 MiB image, engine as
  the image entrypoint) serving the OFFICIAL `Qwen/Qwen3.8-Flash-Next-FP8`
  checkpoint at NATIVE precision — converted no-recipe to
  `qwen4exp-fp8-native.rad` (~161 GiB) after dropping `quantization_config`
  in a staging dir (the plugin descriptor-selection law: nothing claims
  `(qwen4exp, "fp8")`, the shipped plugin claims `(qwen4exp, "")`;
  per-weight encodings are data, not the descriptor) — on BOTH R9700s
  **TP=2** (`--tp-wire wht6` fused all-reduce), experts in a 40 GiB/rank
  pinned host pool + VRAM cache (ratio 0.82 = the measured 99 %-hit point),
  the 47.7 GiB PLE n-gram table PINNED to host RAM (`--ngram-placement
  ram`), fp8 KV 7.32 KiB/token, MTP spec decode depth 3, 2 × 200,000 first
  boot, froggeric v22.5 template, vision + tools + `reasoning_content` auto,
  `/metrics` scraped. Rollback: git tag
  `frank-primary-freetoken-pr587-20261005` (FreeToken image + orcarouter
  payload on disk); older rollback `frank-primary-vllm-shapeG-20261003`
- [[frank-primary-freetoken-pr587]] — **RETIRED 2026-10-05 (same day;
  rollback target)**: FreeToken at PR #587 head `77a7201` (branch
  rocm714_torch214) built on the host into the local image
  `frank-primary-freetoken:pr587-77a7201` (Dockerfile: digest-pinned
  rocm/pytorch rocm7.14 torch-2.11.0 base, libhiprtc dev-symlink law,
  curated --no-deps install per docs/install_amd.md), serving the SAME
  orcarouter FP8 payload on ONE R9700 — experts in pinned host RAM
  (~120 GiB + 47.7 GiB PLE), GPU LRU at 0.10, KV pool 299,968 tokens
  (multiple-of-64 law), 2 slots, parsers AUTO (thinking →
  `reasoning_content`). Measured: boot ~2.3 min, decode 17.1 tok/s
  single-stream, vision "Red" probe passes, native tool_calls; TP=2 does
  not boot on ROCm (pynccl JIT) — second card idle. Superseded by the
  radiance swap for TP=2; the image + payload stay on disk until the
  rollback window closes
- [[dankserver-qwen38-fp8-expert-offload-tuning]] — **RETIRED 2026-10-05
  (rollback target; the vLLM trio + env lore live in the tag)**: the
  tcclaviger RDNA4
  vLLM fork serving orcarouter/Qwen3.8-Flash-Next-Uncensored-FP8 across both
  R9700s, TP=2 with automatic expert offload — `--max-model-len 200704` x 3
  slots, fp8 KV, pool 3,150,000,000 B/rank (measured 398,658 tokens = 1.99x),
  MNBT 1024, gather 32x64, no spec decode, prefetch off, plus
  `--expert-precise-memory` (arena 17.22 GiB / 7,522 slots), GPU_MAX_HW_QUEUES=2
  and a mounted compile cache. Why `--max-num-seqs`
  must stay 3 (SEQS 2 cannot compile this model), why the arena's levers are
  `max_model_len` and the overhead term rather than the KV pool, and the measured envelope
- [[frank-primary-glm53-flash-w4a16]] — RETIRED 2026-09-30 → 10-01 (the
  failed GLM experiment; frank-primary runs Qwen FP8 again, see the intro):
  the tcclaviger RDNA4 vLLM fork
  (digest-pinned `tcclaviger/vllm@sha256:da4029666…`, plain `podman run`,
  no shim) serving Intel/GLM-5.3-Flash-W4A16-AutoRound — AutoRound symmetric
  int4 group 128, ~170 GiB, 34 shards + 2 extras, 113,074 tensors — on BOTH
  R9700s, TP=2, with the MoE experts offloaded to pinned host RAM (12,096
  experts/rank, 73.64 GiB) behind a 14.51 GiB / 2,383-slot VRAM LRU arena; the
  MoE kernel is libr4d's grouped W4A16 GEMM (`R4dW4a16MoEMethod`, reached
  because the checkpoint's `quant_method: auto-round` is overridden to `inc` —
  a compressed-tensors W4A16 checkpoint of the same model has NO offload recipe
  and refuses to serve). 131,072 ctx x 2 seqs, bf16 KV, util 0.98, prefix
  caching, vision and `glm47` tool/reasoning parsers, MTP OFF and prefetch OFF
  by measurement. **Measured decode 9.9-10.0 tok/s, prefill 918 tok/s — the
  35 tok/s target is NOT met, bounded by the fork's expert-gather read path
  (~8.2 GB/s effective vs a 22.74 GB/s link) at a 0.53-0.66 cache hit rate.**
  Rollback: commit `2339fae` (the qwen FP8 + MTP4 shape of 2026-09-29 → 09-30)
- [[frank-primary-r9v-radiance-qwen38-q8]] — RETIRED 2026-09-30 (two swaps
  back; payload and R9V state dirs intact on disk, git tag
  frank-primary-r9v-q8-20260929 is the last pre-cutover commit):
 [[frank-primary-r9v-radiance-qwen38-uncensored]] — RETIRED 2026-09-27
  (same-day swap to the Q8_0 payload; rollback target, state + payload
  intact on disk): the R9V radiance-vLLM fork serving
  Dyluhn/Qwen3.8-Flash-Next-Uncensored-R9V-IQ4_XS (92.39 GiB, 3 shards) +
  blockfp8 MTP4 (depth 4) + F16 vision on BOTH R9700s — TP=2 tiered
  experts (UVA pinned host copy, 62 hot + 160-slot LRU on rank 0, 428
  static on rank 1), PLE n-gram on ssd-mmap, CED on, 196608 ctx. Cut over
  from llama.cpp the same day; rollback target
  [[frank-primary-llamacpp-qwen38-flash-next-q8]]
- [[frank-primary-llamacpp-qwen38-flash-next-q8]] — RETIRED 2026-09-27
  (rollback target; the llama.cpp b11030 endpoint of 2026-09-26):
  unsloth llama.cpp (b11030-mix prebuilt, ROCm gfx120X, bundled runtime)
  serving unsloth/Qwen3.8-Flash-Next-GGUF at Q8_0 across both R9700s —
  routed experts and the 51B-param n-gram table computed in host RAM
  (`-ot exps=CPU,per_layer_token_embd.weight=CPU`), the shared Q8_0 MTP head
  (depth 2) chained behind ngram-mod, BF16 vision, one full 262,144-token
  conversation, `reasoning_content`, the placement law, the cutover and
  rollback
- [[frank-primary-lucebox-ds4]] — RETIRED 2026-09-26 (same-day swap,
  rollback target; active for hours): the Lucebox DS4.1 engine
  (localhost/lucebox-rocm:gfx1201) serving
  Lucebox/DeepSeek-V4.1-Flash-ROCMFP23 (377.2 GiB) with streamed experts —
  the fleet's only non-llama.cpp runtime detour
- [[dankserver-frontier-moe-feasibility]] — VERIFIED 2026-09-28: which of
  DeepSeek-V4.1-Flash (552B), MiMo-V2.6-Flash-MOPD (309B) and GLM-5.3-Flash
  (320B) can run on the 2x R9700 box, on what runtime, and why V4.1 does not
  fit (475 GiB payload, 189 GiB of it Engram; decode is PCIe-expert-stream
  bound, ~23 tok/s ceiling at today's residency). Includes the Affinity
  V4-Flash-to-V4.1 port assessment — reusable expert tiering, four
  architecture gaps, one of them a silent-wrongness trap on the Engram key
- [[dankserver-qwen38-fp8-expert-offload-tuning]] — VERIFIED 2026-09-29:
  the flag-level decode-tuning campaign on the ad hoc qwen-fp8 container
  (tcclaviger RDNA4 fork, orcarouter/Qwen3.8-Flash-Next-Uncensored-FP8,
  TP=2 across both R9700s). **>35 tok/s MET: 37.44-40.57 tok/s with
  `--expert-prefetch` DELETED** — telemetry measured the prefetcher at
  36% precision, wasting ~half the gather traffic (the LRU itself runs at
  82.45% hit). Prefetch-on incumbent 26.8 survived every other challenger
  (geometry, spec depth, TunableOp-corrupts, batch knobs, concurrency,
  ngram-fork-bug); the residual gap to ~60 tok/s is the fork's gather
  read path (6.5-9.5 GB/s effective vs 22.7 at the same slab size)
- [[frank-medium-radiance-mxfp4]] — RETIRED 2026-09-26 (replaced by
  [[frank-primary-lucebox-ds4]], then
  [[frank-primary-llamacpp-qwen38-flash-next-q8]]): vllm-radiance 0.9.3
  serving just1moremodel/Qwen3.8-27B-Uncensored-MXFP4-awq (MXFP4/quark
  W4A8) with the z-lab DFlash2-FP8 drafter as ONE tensor-parallel process
  (TP=2) behind :7770, on unquantized bf16 KV (`KV_DTYPE=auto`, cut
  2026-09-21). The FP8 checkpoint is the on-disk rollback. The three-arm
  battery that chose TP=2, the auto-sized KV pool, and the verified
  capability battery (tools, reasoning)
- [[frank-medium-model-swap]] — how to swap the checkpoint behind frank-medium:
  the streamlining toolchain (hf-manifest.py, hf-fetch.sh,
  swap-frank-medium.sh), the quantization-aware entrypoint contract, the
  quadlet edit, the deploy, the capability battery, and the rollback path.
  The 2026-09-20 MXFP4 → FP8 swap is the worked example
- [[frank-medium-llamacpp-dflash2]] — RETIRED 2026-09-16 → 2026-09-20: mainline
  llama.cpp serving orcarouter/Qwen3.8-27B-Uncensored-GGUF at Q8_0 with the
  DFlash2 Q4_K_M drafter as ONE layer-split process (32:33 over two
  163,840-token slots); superseded by the radiance TP=2 cutover, and the
  rollback target. Keeps the batch/ubatch optimum curve and the per-layer split
  arithmetic
- [[Dual-R9700-Cooperation]] — whether the two R9700s can serve ONE model: the
  RCCL/PCIe-atomics wall on the old TUF GAMING B650-E, the 2026-09-20 ProArt
  B850-Creator x8/x8 swap that cleared it, and the measured three-way verdict
  (radiance TP=2 95.8 t/s decode vs layer split 45.7 vs llama tensor mode 30.5)
  that put TP=2 in production
- [[frank-medium-rocmfpx]] — PRIOR frank-medium deployment (llama.cpp era,
  2026-09-15): charlie12345/ROCmFPX serving
  kingjones777/Qwen3.8-27B-ROCmFPX-Q8_0-AGENT-GGUF; kept as the record of the
  runtime it replaced
- [[freetoken-frank-small]] — RETIRED 2026-09-15, when the RTX 3090 moved to
  frank-large: the FreeToken v0.1.2 frank-secondary runbook (batsclamp
  Huihui-Qwen3.6-35B-A3B-abliterated-FP8), kept as the retirement record. The
  NAME was reused on 2026-09-16 by a different service on Dankclaw — see
  [[frank-secondary-qwen38-gsq-rco]]
- [[freetoken-benchmark-sweep]] — KV pool vs decode speed sweep
  (bs1/bs3/bs4/bs6, 8k–700k KV) on Dankserver RTX 3090
- [[deployment]] — deploy and update process for both servers
- [[frank-redo-2026-08-17]] — the 2026-08-17 topology change
- [[frank-large-rocmfpx-q6agent-uncensored-mtp]] — **RETIRED 2026-10-03 →
  10-05 (rollback target; payload, fork build and build script on disk)**:
  the pinned ROCmFPX fork serving the uncensored protected-heads
  Q6_0_ROCMFPX_AGENT rung with the repo's MTP-Q4_0 head drafting 4 tokens,
  one 262,144 window, f16 KV; measured 27.6-28.1 t/s prose decode at 86.8 %
  acceptance. Replaced by the halogen DFlash2 endpoint; the ngram-mod-onto-MTP
  rejection (-15 %, recurrent-state rollback) stays a live lesson for this
  architecture.
- [[frank-large-rocmfpx-q8agent-mtp]] — **RETIRED 2026-10-02 → 10-03 (the
  rollback target; payload still on disk)**: the same pinned ROCmFPX fork
  serving the ALIGNED `Q8_0_ROCMFPX_AGENT` (ftype 115, 17.0 t/s, MTP
  acceptance 0.462) — the MTP-vs-none +123 % A/B, the trap catalogue
- [[frank-large-gufo-qwen38-27b]] — **RETIRED 2026-10-02 (history; the
  payload dirs were removed from disk 2026-10-03, so this rollback is a
  re-download)** (root systemd unit, port 7770): gufo
  (gufo-org/gufo) v0.1.1, the Strix Halo inference engine, built from
  source on Dankclaw, serving unsloth/Qwen3.8-27B-GGUF **UD-Q4_K_XL**
  with the z-lab DFlash2 Q4_K_M drafter — ONE session at the full native
  262,144 window, unquantized f16 KV. Rolled back by Frank after one day
  of [[frank-large-vllm-mimo-v26-bf16]]. The two from-source build
  workarounds, the client-contract delta, the measured prefill/decode
  trade against llama.cpp
- [[frank-large-vllm-mimo-v26-bf16]] — RETIRED 2026-10-01 (one day;
  rollback by Frank after the autoresearch loop): the digest-pinned
  kyuz0/vllm-therock-gfx1151 image serving
  XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B in FULL BF16, 4 x 262144 ctx,
  CROSS-MODEL MTP from Qwen/Qwen3.5-9B — kept for the measured record:
  battery decode 6.19 t/s (MTP-2) vs 9.01 t/s (no draft — spec NET-
  NEGATIVE on real chat+reasoning traffic), the roof math, the greedy-text
  numerics trap, and the death of every ≥6-bit vLLM quant path on gfx1151
  (quark int8 rejected, FP8 kernels CDNA-only, torchao unwired)
- [[frank-large-unsloth-qwen38-27b-q8xl]] — RETIRED 2026-09-28 (replaced by
  [[frank-large-gufo-qwen38-27b]]; rollback target): stock llama.cpp
  (unsloth b11030, ROCm gfx1151) serving
  unsloth/Qwen3.8-27B-GGUF:UD-Q8_K_XL with the z-lab DFlash2
  Q4_K_M drafter (depth 4) on the gfx1151 iGPU — one full 262,144-token
  conversation, q8_0 KV (the build lacks fp8), text-only, Qwen-Sharp
  v22.4.0 template, the 114 GiB GTT memory model, client contract,
  troubleshooting
- [[frank-large-kairic-edge-qwen38-27b]] — RETIRED 2026-09-21 (same-day
  swap, replaced by [[frank-large-unsloth-qwen38-27b-q8xl]]; rollback
  target): the Kairic Edge runtime (ciru-ai/ROCmFPX v1.2, built from
  source) serving jcbtc/Qwen3.8-27B-IU4-Kairic-Edge (IU4 W4A4, 27B dense)
  on the gfx1151 iGPU — one full 262,144-token conversation, MTP depth 4 +
  n-gram drafting, the three PromptForge sidecars, compatibility mode, the
  114 GiB GTT memory model, client contract, troubleshooting
- [[frank-large-unsloth-qwen38-flash-next]] — RETIRED 2026-09-21 (same-day
  swap, replaced by [[frank-large-kairic-edge-qwen38-27b]]; rollback target):
  the unsloth llama.cpp prebuilt (b11030-mix-5ff778e, ROCm gfx1151) serving
  unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ4_XS (125B MoE) on the gfx1151 iGPU —
  one 200,000-token conversation, MTP depth 2 via the explicit -md shared-Q8_0
  head, the 114 GiB GTT memory model, client contract, troubleshooting
- [[frank-large-ciru-orca]] — RETIRED 2026-09-21 (replaced by
  [[frank-large-unsloth-qwen38-flash-next]]; rollback target): the CIRU
  v4.4.1 runtime (private host build, QSA hotfix) serving
  jcbtc/Qwen3.8-Flash-CIRU-STRIX-Orca w4b on the gfx1151 iGPU — one
  262,144-token conversation, MTP depth 4, 4096 MiB PLE cache, runtime-root
  gate, client contract, troubleshooting (2026-09-19 → 09-21)
- [[halogen-flash-server]] — RETIRED 2026-09-19 (replaced by
  [[frank-large-ciru-orca]]; rollback target): peonist-ai halogen-flash-server
  0.5.8 serving peonist-ai/halogen-qwen3.8-flash-next (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,
  troubleshooting (2026-09-16 → 09-19)
- [[frank-secondary-llama-mimo-q6k]] — **RETIRED 2026-10-01 → 10-02** (the same
  rung returned ACTIVE 2026-10-03 at the 2 x 200,704 f16-KV shape —
  [[frank-secondary-llama-mimo-q6k-2x200704]]): llama.cpp (master, CUDA sm_86
  build) serving
  bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF **Q6_K** on the RTX 3090 — TWO
  native 262,144-token sessions with ASYMMETRIC KV (K f16 unquantized + V
  q8_0, which forces flash-attn), ~20.9/24.6 GiB measured, text-only (the
  GGUF has no vision), reasoning_content, no spec decode; payload still at
  `/home/dank/models/MiMo-Q6K/`
- [[frank-secondary-sglang-mimo-v26]] — RETIRED 2026-10-01 (hours; replaced
  by [[frank-secondary-llama-mimo-q6k]] for the asymmetric KV SGLang cannot
  express; venv still on disk, INT8 payload staged to
  `~dank/.AGENTTRASH/20261002-retired-llm-payloads/`): SGLang in a
  self-contained python3.12 venv serving leteschlead MiMo-V2.6 INT8
  W8A16 AutoRound, 2 x 262144 ctx, fp8 KV, in-checkpoint vision,
  83.9 tok/s decode
- [[frank-secondary-gemma4-12b]] — RETIRED 2026-09-17 → 2026-10-01 (replaced by
  [[frank-secondary-sglang-mimo-v26]] → the llama.cpp MiMo shape; payload staged
  to `~dank/.AGENTTRASH/20261002-retired-llm-payloads/Gemma4-12B-QAT/`):
  mainline llama.cpp serving
  HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced Q4_K_M on the RTX
  3090, with the separate MTP assistant sidecar chained behind ngram-mod,
  q8_0 KV, and `--fit` sizing the full 262k window into ~12 GiB.
- [[frank-secondary-vllm-gemma4]] — RETIRED 2026-09-19 (same-day revert,
  rollback target): vLLM serving google/gemma-4-12B-it-qat-w4a16-ct (w4a16
  Marlin) with the bf16 MTP assistant on the RTX 3090 — bf16 KV, 289,647-
  token pool, 2 concurrent full-context sessions, native text+image+audio.
- [[frank-secondary-qwen38-gsq-rco]] — RETIRED 2026-09-17 (rollback target): the
  prior frank-secondary runbook (2026-09-16 → 09-17), ISTA-DASLab
  Qwen3.8-27B-GSQ-RCO IQ3_S with the model's own in-file MTP head and
  f16 KV at 131k
- [[x4-pair-experiment]] — MEASURED 2026-09-16: what mainline llama.cpp can and
  cannot do with the 3090 + Strix Halo pair, over their only link (the 3090's
  Gen4 x4). The tensor inventory that decides any split, the single flag (`-ot`)
  that kills per-tensor placement across devices, the two-device layer splits
  that work (+7 % decode at 64k, cross-vendor included), the harness-parsing trap
  that invalidated the first round, and the iGPU-only result that matches
  halogen's deployed decode rate — at a memory cost the co-tenants cannot pay
- [[frank-large-ik-uncensored]] — RETIRED 2026-09-16 (rollback target): the
  ik_llama.cpp runbook (root systemd unit, 2026-09-15 → 09-16) serving
  mradermacher/Qwen3.8-Flash-Next-Uncensored-i1-Q4_K_M on the RTX 3090
  (dense/attention/KV) + LPDDR (experts/PLE) hybrid; its measured envelope and
  decode root-cause chain are the record of why the fleet went back to halogen
- [[dankclaw-iommu-translation-off]] — why Dankclaw boots with
  `amd_iommu=off` since 2026-09-11 (13-16 % prefill, measured upstream),
  what it cost (the NPU endpoint), what was deliberately not copied from
  the reference machine, and how to revert
- [[kingjones-strix-rocmfp4]] — PRIOR frank-large runbook and rollback
  target: kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF, 177B params
  (56B MoE + 51.2B PLE), single 113.47 GiB GGUF, on the card's pinned
  kingjones30/ROCmFPX fork (2026-08-30 → 2026-09-11)
- [[ubatch-benchmark-large]] — active-model llama-bench ubatch sweep plan and results
- [[frank-medium-batch-ubatch]] — batch/ubatch sweep on the 2x R9700 layer split
  (2026-09-16): the ubatch optimum at 512, why the logical batch is free, and
  the split rebalance that followed it
- [[kingjones-q8agent-rocmfpx]] — the retired Q8_0-AGENT investigation and `set_rows` failure
- [[eemin-rocmi4-mtp]] — the former caf-eemin Qwen3.8-27B embedded-MTP model
  on Dankclaw (retired)
- [[dealign-ornith-crack]] — the retired Ornith-1.5-35B-A3B CRACK model on
  Dankserver (frank-secondary, retired 2026-09-02)
- [[ikllama-ornith-dankserver]] — the retired ik_llama.cpp runtime for
  frank-secondary (2026-08-26): q8_0 + Hadamard KV cache,
  split-mode none (single-GPU), mandatory FA_ALL_QUANTS build flags
- [[kingjones-strix-mtp]] — the former Q6 AGENT runbook (restored 2026-09-01
  after Q8_0 failure, then superseded by the STRIX deployment on 2026-08-27)
- [[ciru-activefpx-promptforge]] — the RETIRED v3 CIRU PromptForge runtime
  on Dankclaw (superseded 2026-08-24 by the kingjones ROCmFP4 model)
- [[kairic-edge]] — the retired Kairic Edge IU4 experiment
  (deployed and reverted 2026-08-22)
- [[Dankserver System Specs]] — the 2x R9700 box (frank-primary)
- [[Dankclaw System Specs]] — the Strix Halo gfx1151 box (frank-large on
  the flash-server v2 runtime since 2026-10-06, frank-secondary on the RTX 3090)
- [[frank-npu]] — RETIRED 2026-09-11: the FLM NPU sight+sound endpoint
  on Dankclaw (Gemma4 E4B vision+audio pack, XDNA2, port 7771), kept as
  the retirement record — the IOMMU/SVA err=-19 root cause and where
  every dependent route moved

## CIRU Reference (Dankclaw)

- [[ciru-activefpx-promptforge]] — the RETIRED v3 model, ROCm 7.15 toolchain,
  and build history (on Dankclaw; the slot now serves the kingjones
  ROCmFP4 model, see [[kingjones-strix-mtp]])
- [[kairic-edge]] — Kairic Edge IU4 runtime: build runbook, binary
  identity, and experiment summary (retired 2026-08-22)

## DFlash2 Reference (archived)

- [[dflash2-large-vulkan]] — the retired DFlash2 Vulkan deployment
  (2026-08-21)

## 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 (this architecture family is what the retired frank-secondary
  served in the Huihui abliterated FP8 variant — see
  [[freetoken-frank-small]]; the Ornith-1.5-35B-A3B CRACK checkpoint
  that preceded it is archived at [[dealign-ornith-crack]])

## 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-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]] — index of multi-node inference research. The PP
  pair is retired. These pages are research history.

## Runtime Research (llama.cpp family)

- [[Llama Cpp Runtimes]] — mainline vs charlie12345/ROCmFPX vs ik_llama.cpp: positioning, quantization, server fit
- [[Llama Cpp Code Diff]] — code-level quantization diff of the three runtimes + server recommendations
- [[SGLang]] — the structured-generation serving engine; when it fits Dankserver (2x R9700) vs Dankclaw (Strix Halo)

## Cross-Cutting References (skill distillation, 2026-10-05)

One polished reference page per skill-cluster, distilled from the managed
skill library into the vault (see [log](../log.md) for the wave plan):

- [[GGUF Compatibility]] — what a GGUF's tensor histogram and header demand
  of a loader; how the runtime is chosen by the file
- [[Llama Cpp Serving Sizing]] — slot/pool/KV sizing laws, boot-shape
  laddering, llama-bench discipline
- [[Llama Cpp Multi-Device Splits]] — layer vs tensor splits, `-ts`/`-ot`
  laws, drafter placement
- [[PCIe Link and Atomics]] — the link walls, atomics routing, and the
  heterogeneous-pair verdicts
- [[RDNA4 Container Serving]] — bring-up recipes for RDNA4 containers
- [[RDNA4 MoE Expert Offload VRAM Budget]] — the plan law, every arena
  lever, and why free VRAM is not arena
- [[vLLM Boot Forensics and Config Interrogation]] — reading a boot that
  died, and interrogating a running fork's config
- [[vLLM Porting and Compile Triage]] — porting checkpoints across vLLM
  versions/forks; torch.compile/dynamo breakage triage
- [[LLM Bench Windows and Measurement]] — window discipline, honest A/B,
  the window script laws
- [[LLM Performance Diagnosis]] — slow prefill/decode triage on live
  endpoints, IBS attribution, prefix-cache routing
- [[Model Swap and Rollback]] — the swap procedure, payload preflight,
  research verification, second-endpoint bring-up
- [[Tcclaviger Fork Ops]] — the fork's sweep harness, measured knob
  verdicts, large-MoE recipe, compile-cache persistence
- [[Heterogeneous Split Triage]] — triage for unequal-accelerator split
  proposals (the no-go verdict format)
- [[FreeToken Builds]] — the CUDA and ROCm build paths with their
  dependency traps

These sit alongside the operational pages under
`../Operations/index.md` and `../Agent/index.md`.

## Related

- [Project knowledge base](../index.md) — the Podman app stacks on the same
  two hosts. OpenWebUI (Dankclaw) consumes the on-host `frank-large`
  endpoint at `:7770`. The Gitea instance on Dankclaw hosts this repository.
- [Deployment Flow](../Architecture/Deployment%20Flow.md) — the service-scoped
  git-based deploy with inference isolation