rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)
Cross-cutting rename of the current llama.cpp endpoint on the RTX 3090
(port 7771) from frank-small to frank-secondary:
- Service trio: scripts/{frank-small.env,frank-small.service,
serve-frank-small.sh,download-frank-small.sh} → frank-secondary.*
- Test: tests/frank_small_unit.bats → tests/frank_secondary_unit.bats
- Runbooks: serverAppConfigs-docs/LLM/frank-small-*.md →
frank-secondary-*.md (9 files); the FreeToken runbook stays
freetoken-frank-small.md (it documents the retired CUDA-era service)
- Identifiers: FRANK_SMALL→FRANK_SECONDARY, llm_small→llm_secondary,
LLM_SMALL_*→LLM_SECONDARY_*, deploy_llm_small→deploy_llm_secondary
- Historical references to the OLD frank-small (FreeToken/CUDA on the
3090, and the Dankserver service that became frank-medium) are
preserved verbatim — they describe what the service was called
at the time.
This commit is contained in:
Frank
+25
-25
@@ -90,7 +90,7 @@ service_is_allowed() {
|
||||
dankclaw:authentik-postgres|dankclaw:authentik-server|\
|
||||
dankclaw:authentik-worker|dankclaw:authentik-outpost|dankclaw:authentik-outpost-ldap|dankclaw:anubis|\
|
||||
dankclaw:caddy|dankclaw:homepage|dankclaw:seerr|dankclaw:marreta|\
|
||||
dankclaw:frank-large|dankclaw:frank-small|\
|
||||
dankclaw:frank-large|dankclaw:frank-secondary|\
|
||||
dankserver:romm-mariadb|dankserver:romm-redis|dankserver:romm|\
|
||||
dankserver:copyparty|dankserver:jellyfin|dankserver:calibre-web|dankserver:calibre-server|dankserver:plex|dankserver:tautulli|\
|
||||
dankserver:prowlarr|dankserver:qbittorrent|dankserver:radarr|\
|
||||
@@ -1202,7 +1202,7 @@ deploy_llm_large() {
|
||||
# `podman run --name frank-large-halogen` / `podman wait` but NOT in
|
||||
# this deployer's own command line (`bash deploy-remote.sh
|
||||
# frank-large`) — so it cannot shoot itself in the foot (the fleet
|
||||
# pkill law), and it can never match frank-small's llama-server.
|
||||
# pkill law), and it can never match frank-secondary's llama-server.
|
||||
run_privileged systemctl stop frank-large.service 2>/dev/null || true
|
||||
pkill -f 'frank-large-halogen' 2>/dev/null || true
|
||||
podman rm -f frank-large frank-large-halogen >/dev/null 2>&1 || true
|
||||
@@ -1216,57 +1216,57 @@ deploy_llm_large() {
|
||||
wait_for_health frank-large http://127.0.0.1:7770/health 1200
|
||||
}
|
||||
|
||||
# deploy_llm_small — frank-small is llama.cpp (master build, CUDA sm_86) on
|
||||
# deploy_llm_secondary — frank-secondary is llama.cpp (master build, CUDA sm_86) on
|
||||
# the RTX 3090 as a ROOT unit: the runtime is a native binary tree under
|
||||
# ~/GitPackages/llama-master/build-cuda, so there is no container image and
|
||||
# no generated unit to avoid. relink_unit points
|
||||
# /etc/systemd/system/frank-small.service at the repo file and boot
|
||||
# /etc/systemd/system/frank-secondary.service at the repo file and boot
|
||||
# persistence is that unit's [Install] section.
|
||||
#
|
||||
# It is a SEPARATE endpoint on port 7771; frank-large keeps 7770. The 3090 is
|
||||
# not shared: frank-large's engine runs on the gfx1151 iGPU.
|
||||
LLM_SMALL_MODEL_FILE="${LLM_SMALL_MODEL_FILE:-/home/dank/models/Swift15-UncIQ3XXS/Swift-1.5-Qwen3.8-27B-Uncensored-Dynamic-MTP-RCO-IQ3_XXS.gguf}"
|
||||
LLM_SMALL_RUNTIME="${LLM_SMALL_RUNTIME:-/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server}"
|
||||
LLM_SECONDARY_MODEL_FILE="${LLM_SECONDARY_MODEL_FILE:-/home/dank/models/Swift15-UncIQ3XXS/Swift-1.5-Qwen3.8-27B-Uncensored-Dynamic-MTP-RCO-IQ3_XXS.gguf}"
|
||||
LLM_SECONDARY_RUNTIME="${LLM_SECONDARY_RUNTIME:-/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server}"
|
||||
# The projector IS the vision capability here: the GGUF carries no vision
|
||||
# tensors, and the publisher ships mmproj-BF16.gguf in the same repo, so a
|
||||
# deploy that starts without this file silently ships a text-only
|
||||
# endpoint. Checked unconditionally, like frank-large's.
|
||||
LLM_SMALL_MMPROJ="${LLM_SMALL_MMPROJ:-/home/dank/models/Swift15-UncIQ3XXS/mmproj-BF16.gguf}"
|
||||
LLM_SECONDARY_MMPROJ="${LLM_SECONDARY_MMPROJ:-/home/dank/models/Swift15-UncIQ3XXS/mmproj-BF16.gguf}"
|
||||
|
||||
deploy_llm_small() {
|
||||
deploy_llm_secondary() {
|
||||
# Refuse rather than restart-loop: a unit whose runtime or payload is
|
||||
# missing never becomes healthy, and a green deploy would leave the
|
||||
# endpoint dark with nothing in the log to say why.
|
||||
if [[ ! -x "$LLM_SMALL_RUNTIME" ]]; then
|
||||
echo "ERROR: llama.cpp runtime absent at $LLM_SMALL_RUNTIME" >&2
|
||||
echo "frank-small: build it (cmake -B build-cuda -DGGML_CUDA=ON" >&2
|
||||
echo "frank-small: -DCMAKE_CUDA_ARCHITECTURES=86 -DCMAKE_CUDA_HOST_COMPILER=/usr/bin/gcc-13" >&2
|
||||
echo "frank-small: && cmake --build build-cuda --target llama-server) first." >&2
|
||||
if [[ ! -x "$LLM_SECONDARY_RUNTIME" ]]; then
|
||||
echo "ERROR: llama.cpp runtime absent at $LLM_SECONDARY_RUNTIME" >&2
|
||||
echo "frank-secondary: build it (cmake -B build-cuda -DGGML_CUDA=ON" >&2
|
||||
echo "frank-secondary: -DCMAKE_CUDA_ARCHITECTURES=86 -DCMAKE_CUDA_HOST_COMPILER=/usr/bin/gcc-13" >&2
|
||||
echo "frank-secondary: && cmake --build build-cuda --target llama-server) first." >&2
|
||||
return 1
|
||||
fi
|
||||
for f in "$LLM_SMALL_MODEL_FILE" "$LLM_SMALL_MMPROJ"; do
|
||||
for f in "$LLM_SECONDARY_MODEL_FILE" "$LLM_SECONDARY_MMPROJ"; do
|
||||
if [[ ! -f "$f" ]]; then
|
||||
echo "ERROR: frank-small payload file absent at $f" >&2
|
||||
echo "frank-small: run scripts/download-frank-small.sh first;" >&2
|
||||
echo "frank-small: refusing to start a unit that cannot load." >&2
|
||||
echo "ERROR: frank-secondary payload file absent at $f" >&2
|
||||
echo "frank-secondary: run scripts/download-frank-secondary.sh first;" >&2
|
||||
echo "frank-secondary: refusing to start a unit that cannot load." >&2
|
||||
return 1
|
||||
fi
|
||||
done
|
||||
relink_unit frank-small
|
||||
relink_unit frank-secondary
|
||||
run_privileged systemctl daemon-reload
|
||||
run_privileged systemctl enable frank-small.service
|
||||
run_privileged systemctl restart frank-small.service
|
||||
wait_for_health frank-small http://127.0.0.1:7771/health 900 || return 1
|
||||
run_privileged systemctl enable frank-secondary.service
|
||||
run_privileged systemctl restart frank-secondary.service
|
||||
wait_for_health frank-secondary http://127.0.0.1:7771/health 900 || return 1
|
||||
# False-green hardening (frank-large's lesson): the port answering
|
||||
# proves nothing about WHO answers — the unit must be active with a
|
||||
# live MainPID, or a stray SGLang holdover is masquerading as deployed.
|
||||
local main_pid
|
||||
main_pid="$(run_privileged systemctl show -p MainPID --value frank-small.service)"
|
||||
main_pid="$(run_privileged systemctl show -p MainPID --value frank-secondary.service)"
|
||||
if [[ -z "$main_pid" || "$main_pid" == "0" ]]; then
|
||||
echo "FAIL: :7771 answered but frank-small.service has no MainPID — a stray process holds the port" >&2
|
||||
echo "FAIL: :7771 answered but frank-secondary.service has no MainPID — a stray process holds the port" >&2
|
||||
return 1
|
||||
fi
|
||||
echo "frank-small: health answered by unit MainPID $main_pid"
|
||||
echo "frank-secondary: health answered by unit MainPID $main_pid"
|
||||
}
|
||||
|
||||
# deploy_llm_primary — frank-primary is the radiance engine (StillDeadcode,
|
||||
@@ -1567,7 +1567,7 @@ deploy_service() {
|
||||
seerr) deploy_seerr ;;
|
||||
marreta) deploy_marreta ;;
|
||||
frank-large) deploy_llm_large ;;
|
||||
frank-small) deploy_llm_small ;;
|
||||
frank-secondary) deploy_llm_secondary ;;
|
||||
frank-primary) deploy_llm_primary ;;
|
||||
hermes|hermes-dashboard|hermes-webui) deploy_hermes ;;
|
||||
romm|romm-mariadb|romm-redis|mariadb|redis) deploy_romm_stack "$service" ;;
|
||||
|
||||
Reference in New Issue
Block a user