frank-primary: persist rad-tune kernel cache on a host mount

The engine's kernel selector reads $RADIANCE_HOME/tune/<machine>.tune at
boot; $RADIANCE_HOME defaults to /opt/radiance, which lives in the image,
so a cache written by a --rm scratch container dies with it. Pre-create
$FRANK_PRIMARY_STATE_DIR/tune and bind-mount it at
/opt/radiance/share/radiance/tune so the rad-tune cache (generated in a
stopped-service window) survives and is read at every production boot.
This commit is contained in:
Frank
2026-10-06 03:02:51 -07:00
parent bb3532dfec
commit 7fef3cb907
2 changed files with 14 additions and 0 deletions
+5
View File
@@ -59,6 +59,11 @@ FRANK_PRIMARY_IMAGE=stilldeadcode/radiance@sha256:4c3f484564bb2872784e46b0a59cbd
FRANK_PRIMARY_MODEL_DIR=/home/dank/models/rad
FRANK_PRIMARY_MODEL_FILE=qwen4exp-fp8-native.rad
FRANK_PRIMARY_STATE_DIR=/home/dank/radiance-state
# The state dir's tune/ subdirectory holds rad-tune's kernel-selection
# cache (the engine's selector reads $RADIANCE_HOME/tune/<machine>.tune
# at boot; $RADIANCE_HOME defaults to /opt/radiance, in the image, so the
# cache must ride a host mount — serve script mounts it, see the runbook's
# "Tuning levers").
# Container identity is the SERVICE name (Frank's call, 2026-10-05): one
# name across systemctl and podman ps. The runtime changes; the name does
# not. The legacy list retires every predecessor identity that could hold
+9
View File
@@ -101,6 +101,14 @@ mkdir -p "$FRANK_PRIMARY_STATE_DIR/kvcache/frank-primary"
# left the SSD prefix tier off (measured 2026-10-06 boot ledger). Pre-create
# the full path on the host so the tier opens on first boot.
mkdir -p "$FRANK_PRIMARY_STATE_DIR/tune"
# rad-tune's kernel-selection cache (see the runbook's "Tuning levers"):
# the engine's selector reads $RADIANCE_HOME/tune/<machine>.tune at boot;
# $RADIANCE_HOME defaults to /opt/radiance, which lives in the image, so
# the cache must ride a host mount or it dies with the --rm container
# that wrote it. The dir is pre-created for the same reason as kvcache
# (the engine's create is not recursive).
if [ ! -e /dev/kfd ] || [ ! -d /dev/dri ]; then
echo "ERROR: GPU device nodes absent (/dev/kfd, /dev/dri)" >&2
exit 1
@@ -165,6 +173,7 @@ podman run -d --name "$FRANK_PRIMARY_CONTAINER" \
--device /dev/kfd --device /dev/dri \
-v "$FRANK_PRIMARY_MODEL_DIR":/models:ro \
-v "$FRANK_PRIMARY_STATE_DIR":/data \
-v "$FRANK_PRIMARY_STATE_DIR/tune":/opt/radiance/share/radiance/tune \
-v "$FRANK_PRIMARY_TEMPLATE":/templates/template.jinja:ro \
"$FRANK_PRIMARY_IMAGE" \
--model "/models/$FRANK_PRIMARY_MODEL_FILE" \