docs(vault): destroy the dead weight — 53 pages and the change diary

The vault was 155 pages / 31,210 lines, most of it measurement ledgers for
payloads that no longer run. A throughput figure for a runtime nobody operates is
not a record: AI moves faster than the vault, so the number is wrong before
anyone reads it, and a wrong number in a runbook gets believed. Per the new
purpose test in `AGENTS.md` → *Documentation Policy*, it is destroyed.

Gone (`.AGENTTRASH/20261019-destruction/`, KILL-LIST.txt is the manifest):
- the `frank-medium` endpoint and its five era pages, `frank-npu`, FastFlowLM,
  the ikllama/kingjones/dealign/frank-redo eras, the ling/swift15/freetoken/ubatch
  campaign pages, qwen3.8 spec-matrix and strix-optimizations, the two
  "Running Qwen3.6 …" pages;
- the whole `Pipeline Parallelism/` folder (no live script passes a pipeline flag)
  and the multi-device/x4-pair/hybrid/offload experiment pages;
- every vLLM page — no vLLM endpoint exists on this fleet;
- `LLM/deployment.md` (`Architecture/Deployment Flow.md` is the test-referenced
  owner) and the external surveys (SGLang, Lemonade, llama.cpp forks/diff,
  self-hosted app census, the TTS survey) that were obsolete by construction;
- `log.md`, 2,380 lines. Git holds the chronology; a causal law belongs to the
  page that owns the thing it governs, never to a diary.

Survivors: 101 pages, 17,542 lines, 0 OKF violations, 0 unresolved links. Eras
tables keep the window, payload, runtime, reason and rollback pointer; the rate
columns are blanked. The live shapes stay verbatim — those numbers are what the
deployer and `models.yml` consume.

serverAppConfigs-docs/LLM/dankclaw-iommu-translation-off.md

@@ -19,7 +19,7 @@ timestamp: 2026-09-11
 **Current state (since 2026-10-18 01:24): Dankclaw boots `iommu=pt`** — identity
 DMA, IOMMU armed, XDNA2 NPU bound and usable. Everything below is the record of
 the 2026-09-11 decision that booted it with **`amd_iommu=off`** on a vendor-claimed
-13–16 % prefill figure, what that cost, and the measured flip back: see
+13–16 % prefill figure, what that cost, and the measured flip back:
 § *2026-10-18 execution* at the bottom for the numbers and the revert path.
 
 ## What changed
@@ -54,7 +54,7 @@ takes the NPU with it.
 
 1. **The NPU endpoint dies.** With IOMMU off there is no PASID/SVA state and
    `/dev/accel/accel0` cannot be opened — `err=-19`, the exact failure
-   documented in [[frank-npu]]. Audio input left the fleet with it; image input
+   documented in . Audio input left the fleet with it; image input
    survives on `frank-dragoon` through halogen's vision tower.
 2. **Posture change machine-wide.** Dankclaw also serves Caddy (the TLS edge
    and the Anubis/Authentik guard chain), Authentik, Pi-hole, Gitea, and the
@@ -135,7 +135,7 @@ mode**". So `pt` is most of the recovery and PerfOpt is the last part of it.
 
 **The NPU is compatible with identity mode.** `amdxdna` binds through
 `iommu_sva_bind_device()` + PASID + GCR3 into its own `IOPT_TYPE_SVA` domain,
-**independent of the default domain type** (`drivers/accel/amdxdna/aie2_pci.c`),
+**independent of the default domain type** (`drivers/accel/amdxdna/aie2_pci.c`)
 and PerfOpt is not on that path at all. It only needs the IOMMU *enabled* — that
 is the whole `err=-19` story. Kernel pick notes: the Ubuntu 6.17 `-95` SVA
 failures were a GCR3 regression fixed before our kernel, but **6.18–6.18.7
@@ -204,7 +204,7 @@ depth 2, prompt cache ON, no clamp line — and Gitea, the Caddy edge and Grafan
 answered 200. (Later the same day the pool DOUBLING to 401,408 positions for
 slot parity was COMMITTED (`2b12716`) and **deployed the same evening**: the
 boot now reserves `401408 positions (about 11.0 GiB)` and the engine-side total
-is `79.6 GiB in all` (62.9 weights + 11.0 KV + 5.7 working),
+is `79.6 GiB in all` (62.9 weights + 11.0 KV + 5.7 working)
 see [[frank-dragoon]].)
 
 **The NPU came back with the flip.** `amdxdna` bound to `0000:c6:00.1` (Strix/
@@ -212,7 +212,7 @@ Krackan/Strix Halo NPU rev 11), firmware `amdnpu/17f0_11/npu_7.sbin`, `Initializ
 amdxdna_accel_driver 0.7.0 … on minor 0`, IOMMU group 26 `identity`, PASID cap width
 10 (`Exec- Priv-`). `/dev/accel/accel0` is `crw-rw---- root:render 261,0` and `dank`
 is in `render`, so a quadlet needs `AddDevice=/dev/accel/accel0` +
-`GroupAdd=keep-groups`. **No NPU endpoint is deployed** — [[frank-npu]] stays the
+`GroupAdd=keep-groups`. **No NPU endpoint is deployed** —  stays the
 history of the retired endpoint; what changed is only its precondition.
 
 **Deliberately deferred:** the `pp_dpm_fclk` pin (level 7, 2000 MHz) from the issue's
@@ -228,7 +228,7 @@ lives in `~/.local/bin`.
 
 ## Related
 
-- [[frank-npu]] — the endpoint this retired, including the err=-19 root cause
+-  the endpoint this retired, including the err=-19 root cause
 - [[frank-dragoon]] — the runtime bought by the prefill figure
 - [[frank-dragoon]] — the runtime it replaced (rollback target)