# frank-large.service — vLLM MiMo-V2.6-Distill-Qwen-9B (BF16) on the Strix
# Halo gfx1151 iGPU, :7770. 2026-10-01 cutover from gufo (tag
# frank-large-gufo-q4kxl-20261001 restores the Q4_K_XL + DFlash2 shape).
#
# WHY A ROOT UNIT: parity with frank-primary/frank-small — the unit is
# relink_unit'd from this repo into /etc/systemd/system/, PID1 grants
# LimitMEMLOCK=infinity (vLLM pins host buffers), and OOM protection lands
# on the engine instead of the co-tenants. The container runs in dank's
# ROOTLESS podman storage.
#
# The serve script drives `podman run` directly (image entrypoint is
# overridden to `vllm serve`) and blocks on the container, so a container
# death is a non-zero ExecStart. NOTE from frank-primary's experience:
# vLLM's API server can drain and exit 0 after an engine fault, so the
# restart policy MUST be always, not on-failure.
[Unit]
Description=frank-large — vLLM MiMo-V2.6-Distill-Qwen-9B (BF16) on the gfx1151 iGPU
After=network-online.target
Wants=network-online.target
# Never let the start-rate limiter give up after a crash loop.
StartLimitIntervalSec=0

[Service]
User=dank
Group=dank
LimitMEMLOCK=infinity
Environment="FRANK_LARGE_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-large.env"
ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-large.sh
# systemd stop: podman wait alone cannot stop the container child; stop it
# explicitly or the engine outlives the unit holding the GPU and port.
ExecStop=/usr/bin/podman stop -t 120 frank-large-mimo
# Boot cost: ~200-240 s warm (measured 2026-10-01 bench window); cold torch
# compile is longer. Health stays 503 until the engine is up — do not kill.
TimeoutStartSec=1800
# ExecStop allows 120 s of drain; the stop timeout must exceed it (the
# frank-primary 2026-10-01 lesson: a short TimeoutStopSec records 'Failed
# with result timeout' on every stop).
TimeoutStopSec=180
Restart=always
RestartSec=10
# The engine holds 17.5 GiB of weights plus the KV pool in the GTT
# aperture; it is the last process on this host the kernel should pick.
OOMScoreAdjust=-500

[Install]
WantedBy=multi-user.target