docs(frank-tts): record the iGPU cutover, close the NPU question

The cutover PR merged the runtime; this carries the surface that has to be
true afterwards.

- Engine page: the shape is now `--device Vulkan0` on the gfx1151 as a
  co-tenant beside frank-dragoon; the registry/thread/streaming laws gain a
  fourth — the device law — whose numbers stay in the verdict report, and the
  deploy record gets the cutover steps including the `glslc` configure gate.
  The CPU-era arm/rollback prose keeps the qualitative argument and drops the
  dead numbers per the purpose test.
- Endpoint page: "Where the engine computes" now says iGPU + co-tenancy, and
  states the NPU verdict in one paragraph instead of a research tour.
- Quadlet comment: it claimed supplementary groups are what grant render
  access. On this host the udev rule world-writes the render nodes and the
  container's `id` shows no groups at all, so keep-groups is belt-and-braces;
  the RSS note now matches the device shape instead of the CPU trial.
- Verdict report: gate 2 (contention) recorded as measured after the cutover,
  and the build-stage prediction corrected — the package is `glslc`, not
  `libvulkan-dev glslang-dev`.
- index.md regenerated (one description changed).

dankclaw/voiceservice/quadlet/frank-tts-engine.container

@@ -40,19 +40,24 @@
 # speaks to the server from inside its own namespace, which is where the address
 # is valid.
 #
-# MEMORY / THE RENDER NODE. Host RSS stays near the 5.7 GiB the CPU trial
-# measured (weights + context resident); no memory limit is set because the box
-# has the room and a limit would convert a busy moment into an OOM kill
-# mid-utterance.
+# MEMORY / THE RENDER NODE. Host RSS is ~1.7 GiB, not the size of the GGUFs:
+# the Vulkan backend copies both tensors into device memory at load, so they
+# stop counting in the process's RSS (measured after the 2026-10-19 cutover —
+# `podman stats` / `ps -o rss`). No memory limit is set: the box has the room
+# and a limit would convert a busy moment into an OOM kill mid-utterance.
 #
-# `AddDevice=/dev/dri` + `GroupAdd=keep-groups` are what make the iGPU visible,
-# and both are required: a rootless container that drops its supplementary
-# groups has no render permission, and the Vulkan ICD then enumerates nothing —
-# this is the same ride ComfyUI takes (dankclaw/comfyui, plus the udev rule that
-# makes the nodes group-writable). The node is NOT named: this host is hybrid,
-# renderD128 is the NVIDIA card and renderD129 the amdgpu iGPU, so a node number
-# in the unit is a guess that a re-probe can invalidate, while the directory
-# hands the container every render node and the driver picks by name.
+# `AddDevice=/dev/dri` is what makes the iGPU visible; without it the Vulkan
+# ICD enumerates nothing and the server dies on device lookup after it has
+# already read both GGUFs. `GroupAdd=keep-groups` is belt-and-braces, not the
+# thing that works here: the units podman spawns carry no supplementary groups
+# at all, and this host grants render access a different way — the udev rule
+# that makes the render nodes world-writable (same rule ComfyUI rides, see
+# dankclaw/comfyui). Measured: `id` inside this container lists only the
+# container's own group, and `tts-server` still holds renderD129.
+# The node is NOT named: this host is hybrid, renderD128 is the NVIDIA card and
+# renderD129 the amdgpu iGPU, so a node number in the unit is a guess that a
+# re-probe can invalidate, while the directory hands the container every render
+# node and the driver picks by name.
 #
 # /dev/kfd stays absent on purpose: that is the ROCm compute interface, owned by
 # the engines that use HIP. A Vulkan endpoint has no use for it, and handing a