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.
This commit is contained in:
@@ -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
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user