# frank-primary.service — vLLM 0.30 endpoint (Qwen3.8-Flash-Next-FP8,
# UVA offload shape) on the 2x R9700 pair, dankserver :7770.
#
# Replaces the llama.cpp frank-primary unit of 2026-09-26 (same port, same
# served alias; harness models.yml unchanged). The serve script execs a
# podman container (image localhost/frank-primary:vllm030) as dank.
#
# WHY A ROOT UNIT (not a rootless quadlet): the UVA offload pins ~160 GiB of
# host RAM (PLE n-gram table + routed experts). Pinned pages are charged
# against RLIMIT_MEMLOCK; dank's login session on this host carries 8 MiB and
# a user quadlet is capped by the user manager's own hard limit — raising
# that means restarting user@1000.service and bouncing every user container
# on the host. A root unit grants LimitMEMLOCK=infinity to the dank process
# via PID1, no user-manager restart, and the image stays in dank's rootless
# podman storage (podman run as dank reads ~/.local/share/containers).
[Unit]
Description=frank-primary — vLLM 0.30 Qwen3.8-Flash-Next-FP8 (UVA offload) on 2x R9700
After=network-online.target
Wants=network-online.target

[Service]
User=dank
Group=dank
# The UVA offloader pins the offloaded weights in host RAM; an RLIMIT_MEMLOCK
# smaller than the pinned set fails the load mid-start. PID1 grants infinity
# here — parity with the fleet's other LLM units.
LimitMEMLOCK=infinity
Environment="FRANK_PRIMARY_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-primary.env"
ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-primary.sh
# Cold start: Triton/inductor compile (several minutes on first boot) plus
# reading+pinning ~173 GiB of weights. Parity with the radiance-era timeout.
TimeoutStartSec=1800
Restart=on-failure
RestartSec=10

[Install]
WantedBy=multi-user.target