llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

The 2026-10-09 wire aliases become the service names everywhere:
systemd units, serve scripts, env files and FRANK_* variables,
deploy-plan/deploy-remote service keys, container names, Prometheus
job names + alert rules, Grafana dashboard queries, bats seams,
runbook filenames, homepage/AGENTS lore, and historical prose.
Rollback tags renamed in lockstep. Residue in the tree: zero.
Retired frank-medium/small/npu names are history and stay.

Known casualty: scripts/patches/*.patch context lines were rewritten;
those retired-era vLLM-fork patches no longer apply byte-exact.

serverAppConfigs-docs/LLM/eemin-rocmi4-mtp.md

@@ -1,7 +1,7 @@
 ---
 type: reference
 title: caf-eemin Qwen3.8-27B ROCmI4 embedded MTP on Dankclaw
-description: caf-eemin/Qwen3.8-27B-ROCmI4-MTP-GGUF (Q4_0_ROCMI4, embedded NextN/MTP head) served by the charlie12345/ROCmFPX llama.cpp runtime (ROCmI4 W4A4) on the Strix Halo iGPU. frank-large.
+description: caf-eemin/Qwen3.8-27B-ROCmI4-MTP-GGUF (Q4_0_ROCMI4, embedded NextN/MTP head) served by the charlie12345/ROCmFPX llama.cpp runtime (ROCmI4 W4A4) on the Strix Halo iGPU. frank-dragoon.
 tags:
   - llama.cpp
   - rocm
@@ -15,14 +15,14 @@ timestamp: 2026-08-25
 
 # caf-eemin Qwen3.8-27B ROCmI4 embedded MTP on Dankclaw
 
-> **RETIRED 2026-08-25.** `frank-large` served this model from 2026-08-18
+> **RETIRED 2026-08-25.** `frank-dragoon` served this model from 2026-08-18
 > until 2026-08-25. It replaced the kingjones777 ROCmFP4 STRIX MTP payload
 > on the same port and the same Strix Halo iGPU, running the new
 > charlie12345/ROCmFPX ROCmI4 W4A4 build (see [[kingjones-strix-mtp]] for
 > the page it replaced), and was itself replaced by
 > [[kingjones-strix-rocmfp4]].
 
-`frank-large` (port 7770) serves
+`frank-dragoon` (port 7770) serves
 `cafonz/Qwen3.8-27B-ROCmI4-MTP-GGUF` (published under the public
 `eemin` namespace) from the **charlie12345/ROCmFPX** llama.cpp fork built with
 the opt-in `ROCmI4 W4A4` path. The model is `Q4_0_ROCMI4`: signed four-bit
@@ -98,7 +98,7 @@ graph TD
     D --> E[Sharp chat template<br/>reasoning deepseek]
 ```
 
-Key flags (see `scripts/serve-frank-large.sh`):
+Key flags (see `scripts/serve-frank-dragoon.sh`):
 
 ```
 --spec-type draft-mtp --spec-mtp-strict-qwen
@@ -129,8 +129,8 @@ path's greedy decisions; it does not remove the W4A4 activation approximation.
 
 ### Service
 
-- Unit: `frank-large.service`, port 7770
-- Script: `scripts/serve-frank-large.sh`, env `scripts/frank-large.env`
+- Unit: `frank-dragoon.service`, port 7770
+- Script: `scripts/serve-frank-dragoon.sh`, env `scripts/frank-dragoon.env`
 
 ## Tuning MTP
 
@@ -144,14 +144,14 @@ Decode throughput depends on the ubatch (per-eval token batch). Run the sweep
 on 8k contexts, 512 → 4096 in steps of 512, with a fixed batch:
 
 ```
-sudo systemctl stop frank-large
+sudo systemctl stop frank-dragoon
 ./scripts/bench-ubatch.sh
-sudo systemctl start frank-large
+sudo systemctl start frank-dragoon
 ```
 
-The script stops `frank-large` for a clean GPU, boots one server
+The script stops `frank-dragoon` for a clean GPU, boots one server
 instance per ubatch on a scratch port, reads authoritative `print_timing` tok/s,
-and restarts the service. See [[frank-large-benchmark]].
+and restarts the service. See [[frank-dragoon-benchmark]].
 
 ## Known Issues
 
@@ -185,4 +185,4 @@ The ubatch sweep above gives the production ubatch choice.
 - [[kingjones-strix-mtp]] — the retired ROCmFP4 predecessor on this slot
 - [[ciru-activefpx-promptforge]] — the retired v3 CIRU PromptForge page
 - [[Dankclaw System Specs]] — the box
-- [[frank-large-benchmark]] — backend/spec benchmark history
+- [[frank-dragoon-benchmark]] — backend/spec benchmark history