frank-primary vllm: orphan-container self-heal + HOME + stop/rm order

Unit restart SIGKILLs conmon before --rm cleanup runs, leaving the container
name registered: every restart then dies on name-in-use while the orphan
holds the port and GPUs (observed live 2026-09-27, NRestarts=6 with the
container Up and the unit auto-restarting). The serve script now clears its
own name before exec podman run; the deployer stops the unit and removes
the container BEFORE waiting on the port.

HOME inside the container pointed at the root-owned WORKDIR /app, so
vLLM's registry cache write hit PermissionError; HOME now points at the
cache volume.

The vLLM cutover itself is blocked on a structural wall (AMD Qwen4Exp impl
creates the 51.2B PLE table as a bf16 on-GPU param: 47.69 GiB transient on a
31.86 GiB card; the pinned-host UVA path that fits this hardware is
CUDA-gated). llama.cpp is restored live at :7770; host HEAD unchanged.

scripts/serve-frank-primary.sh

@@ -78,7 +78,7 @@ fi
 
 mkdir -p /home/dank/.cache/frank-primary-vllm
 
-SERVE_ARGS=(serve "$MODEL_DIR"
+SERVE_ARGS=("$MODEL_DIR"
     --served-model-name "$SERVED_NAME"
     --host "$BIND_HOST"
     --port "$PORT"
@@ -99,6 +99,10 @@ SERVE_ARGS=(serve "$MODEL_DIR"
 if [ -n "${SPEC_CONFIG:-}" ]; then
     SERVE_ARGS+=(--speculative-config "$SPEC_CONFIG")
 fi
+# A crashed/killed unit leaves the container name registered (systemd can
+# SIGKILL conmon before the --rm cleanup runs); podman run would then die
+# on name-in-use forever. Clear any orphan of OUR name first — idempotent.
+podman rm -f "$CONTAINER_NAME" >/dev/null 2>&1 || true
 
 exec podman run --rm \
     --name "$CONTAINER_NAME" \
@@ -113,11 +117,13 @@ exec podman run --rm \
     -e ROCR_VISIBLE_DEVICES="$ROCR_VISIBLE_DEVICES" \
     -e HIP_VISIBLE_DEVICES="$HIP_VISIBLE_DEVICES" \
     -e VLLM_ROCM_USE_AITER="$VLLM_ROCM_USE_AITER" \
+    -e NCCL_P2P_DISABLE="$NCCL_P2P_DISABLE" \
     -e TRITON_CACHE_DIR="$CACHE_ROOT/triton" \
     -e TORCHINDUCTOR_CACHE_DIR="$CACHE_ROOT/inductor" \
-    -e VLLM_CACHE_DIR="$CACHE_ROOT/vllm" \
+    -e HOME="$CACHE_ROOT" \
     -e TRITON_ALLOW_NON_CONST_GLOBALS=1 \
     --volume /home/dank/models:/models \
     --volume /home/dank/.cache/frank-primary-vllm:"$CACHE_ROOT" \
     "$IMAGE" \
-    vllm "${SERVE_ARGS[@]}"
+    "${SERVE_ARGS[@]}"
+