sightsound: move FLM NPU endpoint port 52626 -> 7771

Env file is the source of truth (unit ExecStart runs the serve script which
sources it); serve-script default and the deployer health-gate URL flipped in
lockstep so the post-restart health gate polls the new port. Docs, fleet table,
and both index bullets updated to match.
This commit is contained in:
Frank
2026-08-30 14:06:54 -07:00
parent 9b9f0f9051
commit 9ef034e5e6
7 changed files with 10 additions and 10 deletions
+1 -1
View File
@@ -647,7 +647,7 @@ deploy_llm_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 frank-default-sightsound http://127.0.0.1:7771/v1/version 300
}
wait_for_health() {
+1 -1
View File
@@ -9,7 +9,7 @@
# 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
FLM_PORT=7771
# 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.
+1 -1
View File
@@ -30,7 +30,7 @@ fi
: "${FLM_BIN:=/usr/bin/flm}"
: "${FLM_MODEL:=gemma4-it:e4b}"
: "${FLM_HOST:=0.0.0.0}"
: "${FLM_PORT:=52626}"
: "${FLM_PORT:=7771}"
: "${FLM_PMODE:=turbo}"
: "${FLM_ASR:=0}"
: "${FLM_CTX_LEN:=131072}"