sightsound: new FLM NPU sight+sound service on XDNA2 (gemma4-it:e4b)

New Dankclaw service frank-default-sightsound: FLM 1.0.1 serving the
Gemma4-E4B-IT-NPU2 pack (vision+audio+reasoning, 131072 ctx) on the XDNA2
NPU at port 52626. Model choice rationale: gemma4-it is the only NPU2 model
family with BOTH image and audio towers; the uncensored candidate qwythos:9b
is text-only, so sight+sound wins over uncensored here.

Deployer wiring: planner maps env/unit/serve files to the new service name;
deploy-remote gains deploy_llm_sightsound (relink + daemon-reload + enable +
restart + health gate on /v1/version — FLM has no /health route). Unlike the
retired frank-default-npu relink-only path, this unit is boot-enabled.

scripts/deploy-plan.py

@@ -56,6 +56,7 @@ SERVICE_ORDER = (
     "readarr",
     "frank-default-large",
     "frank-default-npu",
+    "frank-default-sightsound",
     "frank-default-small",
 )
 
@@ -84,6 +85,7 @@ DANKCLAW_SERVICES = {
     "homepage",
     "frank-default-large",
     "frank-default-npu",
+    "frank-default-sightsound",
 }
 
 DANKSERVER_SERVICES = {
@@ -304,6 +306,8 @@ def services_for_path(path: str, target: str) -> set[str]:
             _add(services, "frank-default-large")
         elif name in {"frank-default-npu.env", "frank-default-npu.service", "serve-frank-default-npu.sh"}:
             _add(services, "frank-default-npu")
+        elif name in {"frank-default-sightsound.env", "frank-default-sightsound.service", "serve-frank-default-sightsound.sh"}:
+            _add(services, "frank-default-sightsound")
         elif name in {"frank-default-small.env", "frank-default-small.service", "serve-frank-small.sh"}:
             _add(services, "frank-default-small")
         elif name == "chat-template.jinja":

scripts/deploy-remote.sh

@@ -610,6 +610,18 @@ deploy_llm_npu() {
     echo "Relinked frank-default-npu; it was not restarted."
 }
 
+# frank-default-sightsound is a live serving endpoint (FLM on the XDNA2 NPU),
+# not a relink-only unit: it is enabled at boot and restarted on deploy. The
+# health gate polls /v1/version, FLM's cheapest always-on route (there is no
+# /health route in the FLM server).
+deploy_llm_sightsound() {
+    relink_unit frank-default-sightsound
+    run_privileged systemctl daemon-reload
+    run_privileged systemctl enable frank-default-sightsound
+    run_privileged systemctl restart frank-default-sightsound
+    wait_for_health frank-default-sightsound http://127.0.0.1:52626/v1/version 300
+}
+
 wait_for_health() {
     local service="$1" url="$2" limit="$3"
     local i
@@ -646,6 +658,7 @@ deploy_service() {
         frank-default-large) deploy_llm_large ;;
         frank-default-small) deploy_llm_small ;;
         frank-default-npu) deploy_llm_npu ;;
+        frank-default-sightsound) deploy_llm_sightsound ;;
         *) deploy_compose_service "$service" ;;
     esac
 }

scripts/deploy.sh

@@ -121,6 +121,7 @@ valid_service() {
         dankclaw:node-exporter|dankclaw:authentik-postgres|dankclaw:authentik-server|\
         dankclaw:authentik-worker|dankclaw:authentik-outpost|dankclaw:anubis|\
         dankclaw:frank-default-large|dankclaw:frank-default-npu|\
+        dankclaw:frank-default-sightsound|\
         dankserver:mariadb|dankserver:redis|dankserver:romm|dankserver:copyparty|\
         dankserver:jellyfin|dankserver:calibre-web|dankserver:prowlarr|\
         dankserver:qbittorrent|dankserver:radarr|dankserver:sonarr|\

scripts/frank-default-sightsound.env

@@ -0,0 +1,23 @@
+# Tunables for frank-default-sightsound (FastFlowLM NPU sight+sound endpoint, Dankclaw)
+# Runtime: FLM 1.0.1 (/usr/bin/flm) on the XDNA2 NPU (50 TOPS). Model:
+# gemma4-it:e4b = Gemma4-E4B-IT-NPU2 (8B total / ~4.5B effective params,
+# Q4_1; vision + audio + reasoning; ~9.1 GB footprint). It is the only NPU2
+# model family with BOTH an image and an audio tower — the uncensored
+# candidate qwythos:9b is text-only and fails the audio requirement, so this
+# endpoint trades "uncensored" for "sight + sound". The NPU draws from the
+# unified RAM pool shared with frank-default-large (iGPU); ~31 GiB was
+# available there at idle, so a 9.1 GB pack fits with headroom.
+FLM_MODEL=gemma4-it:e4b
+FLM_HOST=0.0.0.0
+FLM_PORT=52626
+# turbo = max NPU power mode (xrt-smi configure --pmode turbo at serve start).
+# No other tenant uses the NPU on this host, so the top mode costs nothing to
+# neighbours; drop to `performance` if iGPU power-budget contention ever shows.
+FLM_PMODE=turbo
+# FLM_ASR=1 additionally loads Whisper-V3-Turbo-NPU2 (+0.62 GB) and exposes
+# /v1/audio/transcriptions. gemma4-it:e4b answers audio natively through its
+# own audio tower in /v1/chat/completions, so ASR stays off by default.
+FLM_ASR=0
+# 131072 = verified max for gemma4-it:e4b on this box (native 128K context;
+# the registry's default_context_length 32768 is only the fallback default).
+FLM_CTX_LEN=131072

scripts/frank-default-sightsound.service

@@ -0,0 +1,17 @@
+[Unit]
+Description=FastFlowLM NPU sight+sound inference (frank-default-sightsound) on Dankclaw
+After=network-online.target
+Wants=network-online.target
+
+[Service]
+Type=simple
+User=dank
+Group=dank
+Environment="FLM_SIGHTSOUND_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-default-sightsound.env"
+ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-default-sightsound.sh
+LimitMEMLOCK=infinity
+Restart=on-failure
+RestartSec=10
+
+[Install]
+WantedBy=multi-user.target

scripts/serve-frank-default-sightsound.sh

@@ -0,0 +1,61 @@
+#!/usr/bin/env bash
+# Serve the FastFlowLM (FLM) sight+sound endpoint — frank-default-sightsound.
+#
+# Runs `flm serve <tag>` on the XDNA2 NPU (50 TOPS, Dankclaw). The NPU is a
+# single-lane device: generations serialize in FIFO order, so this is a
+# background/triage endpoint, not an interactive multi-user chat. The NPU
+# draws from the unified RAM pool shared with frank-default-large (the iGPU
+# llama.cpp service); see serverAppConfigs-docs/LLM/frank-default-sightsound.md
+# for the memory budget and the model-selection tradeoff.
+#
+# NOTE: FLM requires unlimited memlock. The unit sets LimitMEMLOCK=infinity.
+# NOTE: an unknown model tag does NOT 404 — FLM logs an error and silently
+# serves llama3.2:1b instead. Client model IDs must be the exact FLM registry
+# tag (e.g. gemma4-it:e4b), never a service alias. Custom tags only resolve
+# when FLM_CONFIG_PATH points at the user registry that carries them and their
+# kernels are symlinked into /home/dank/.config/flm/xclbins/<PackName>.
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+ENV_FILE="${FLM_SIGHTSOUND_ENV_FILE:-$SCRIPT_DIR/frank-default-sightsound.env}"
+if [[ -f "$ENV_FILE" ]]; then
+    set -a
+    # shellcheck disable=SC1090
+    source "$ENV_FILE"
+    set +a
+fi
+
+# --- defaults (used when the env file does not set them) -------------------
+: "${FLM_BIN:=/usr/bin/flm}"
+: "${FLM_MODEL:=gemma4-it:e4b}"
+: "${FLM_HOST:=0.0.0.0}"
+: "${FLM_PORT:=52626}"
+: "${FLM_PMODE:=turbo}"
+: "${FLM_ASR:=0}"
+: "${FLM_CTX_LEN:=131072}"
+
+# The user registry is a superset of the system registry (it carries the
+# custom tags too), and its model_path resolves relative to the registry file,
+# so exports keep a tag swap in the env file from needing script edits.
+export FLM_CONFIG_PATH="${FLM_CONFIG_PATH:-/home/dank/.config/flm/model_list.json}"
+export FLM_XCLBIN_PATH="${FLM_XCLBIN_PATH:-/home/dank/.config/flm/xclbins}"
+
+if [[ ! -x "$FLM_BIN" ]]; then
+    echo "missing flm binary: $FLM_BIN" >&2
+    exit 1
+fi
+
+# --- optional flags ----------------------------------------------------------
+OPT_ARGS=()
+if [[ "${FLM_ASR}" != "0" ]]; then
+    OPT_ARGS+=(--asr "${FLM_ASR}")
+fi
+if [[ "${FLM_CTX_LEN}" != "-1" ]]; then
+    OPT_ARGS+=(--ctx-len "${FLM_CTX_LEN}")
+fi
+
+exec "$FLM_BIN" serve "$FLM_MODEL" \
+    --host "$FLM_HOST" \
+    -p "$FLM_PORT" \
+    --pmode "$FLM_PMODE" \
+    "${OPT_ARGS[@]}"