frank-medium: swap ROCmFPX llama.cpp runtime for vllm-radiance MXFP4

Rootless Quadlet on dankserver serving
just1moremodel/Qwen3.8-27B-Uncensored-MXFP4-awq (the radiance stack's
designated alternate target; ships its fp8 MTP head, no rewrite step) with
the DFlash2-FP8 drafter at SPEC=7 on the 2x R9700s (TP=2, host network,
:7770, alias frank-medium unchanged).

- dankserver/frank-medium/: quadlet unit, container entrypoint (fork of
  serve-mxfp4.sh's patch block at pinned clone commit 97353293), healthcheck
- dispatcher retires the root llama.cpp unit, re-tags the registry image to
  the localhost alias, installs the quadlet, waits on /health
- planner maps dankserver/frank-medium/* to frank-medium; scripts-era
  mappings removed
- ROCmFPX-era env/serve/unit/download scripts staged in scripts/.AGENTTRASH
  with .rocmfpx suffix; seams updated (frank_medium_quadlet.bats new)

scripts/deploy-remote.sh

@@ -991,34 +991,40 @@ wait_for_llm_large_ready() {
     return 0
 }
 
-# deploy_llm_medium — frank-medium replaced frank-small on 2026-09-15 when the
-# RTX 3090 left the host for two Radeon AI PRO R9700 cards. The old unit is a
-# CUDA-era FreeToken service that can only crash-loop on this hardware, so it
-# is retired here (stop, disable, move the installed unit to the trash) before
-# its replacement starts. Same failure mode as frank-large's retirement: this
-# host's `systemctl disable` has been observed to delete the unit file itself
-# (2026-08-26 incident), so both outcomes are tolerated.
-retire_root_llm_small() {
-    local trash="$HOME/.AGENTTRASH/20260915-frank-small-retire/host-units"
-    run_privileged systemctl stop frank-default-small 2>/dev/null || true
-    run_privileged systemctl disable frank-default-small 2>/dev/null || true
-    run_privileged systemctl stop frank-small.service 2>/dev/null || true
-    run_privileged systemctl disable frank-small.service 2>/dev/null || true
-    if [[ -e /etc/systemd/system/frank-small.service || -L /etc/systemd/system/frank-small.service ]]; then
+# deploy_llm_medium — frank-medium runs as a rootless Quadlet since the
+# 2026-09-15 runtime swap to the vllm-radiance MXFP4 stack. It began the day
+# as a root llama.cpp unit (the ROCmFPX/Q8_0_ROCMFPX_AGENT deployment from
+# the morning GPU swap); that root unit is retired here first — stop,
+# disable, move the installed unit into the home trash. Same failure mode as
+# frank-large's retirement: this host's `systemctl disable` has been
+# observed to delete the unit file itself (2026-08-26 incident), so both
+# outcomes are tolerated.
+retire_root_llm_medium() {
+    local trash="$HOME/.AGENTTRASH/20260915-rocmfpx-retire/host-units"
+    run_privileged systemctl stop frank-medium.service 2>/dev/null || true
+    run_privileged systemctl disable frank-medium.service 2>/dev/null || true
+    if [[ -e /etc/systemd/system/frank-medium.service || -L /etc/systemd/system/frank-medium.service ]]; then
         mkdir -p "$trash"
-        run_privileged mv -- /etc/systemd/system/frank-small.service \
-            "$trash/frank-small.service"
-        echo "retired root unit frank-small.service -> $trash"
+        run_privileged mv -- /etc/systemd/system/frank-medium.service \
+            "$trash/frank-medium.service"
+        echo "retired root unit frank-medium.service -> $trash"
     fi
     run_privileged systemctl daemon-reload
 }
 
 deploy_llm_medium() {
-    retire_root_llm_small
-    relink_unit frank-medium
-    run_privileged systemctl daemon-reload
-    run_privileged systemctl enable frank-medium
-    run_privileged systemctl restart frank-medium
+    retire_root_llm_medium
+    # Pull once, then run the localhost/-aliased tag: this host's quadlet
+    # path cannot resolve registry-prefixed refs from local storage at
+    # create time (same as frank-large on dankclaw). Pull=never keeps boots
+    # off the registry.
+    podman pull docker.io/stilldeadcode/vllm-radiance:0.9.3 >/dev/null 2>&1 || true
+    podman tag docker.io/stilldeadcode/vllm-radiance:0.9.3 localhost/radiance-vllm:0.9.3
+    # The compile cache must exist before the quadlet mounts resolve; the
+    # one-time setup (setup-mxfp4.sh / PREPARE_ONLY) normally creates it.
+    mkdir -p /home/dank/.radiance-cache-w4a8-093-gdnm-nqft-fp8s-gnq/{vllm,inductor,triton,aiter}
+    install_quadlet frank-medium dankserver/frank-medium/quadlet frank-medium
+    systemctl --user restart frank-medium.service
     wait_for_health frank-medium http://127.0.0.1:7770/health 1200
 }