# frank-primary.service — tcclaviger RDNA4 vLLM endpoint
# (Intel/GLM-5.3-Flash-W4A16-AutoRound int4, 131,072 x 2 seqs, bf16 KV, TP=2,
# expert offload to pinned host RAM, 34-shard payload) on the 2x R9700 pair,
# dankserver :7770. 2026-09-30 cutover from orcarouter
# Qwen3.8-Flash-Next-Uncensored-FP8 + MTP4; commit 2339fae is the pre-cutover
# state and the rollback.
#
# Same port, same served alias; the harness models.yml id is unchanged.
# The serve script drives `podman run` directly (the image entrypoint execs
# `vllm serve`) and then waits on the container, so a crashed engine is a
# nonzero ExecStart and Restart=on-failure is real.
#
# WHY A ROOT UNIT (not a rootless quadlet): the expert-offload shape pins
# 73.64 GiB per rank of host RAM (the expert host rows). 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, and the image
# stays in dank's rootless podman storage.
[Unit]
Description=frank-primary — tcclaviger vLLM GLM-5.3-Flash int4 W4A16 on 2x R9700
After=network-online.target
Wants=network-online.target

[Service]
User=dank
Group=dank
# The tiered-expert offloader pins 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
# systemd stop: wait alone cannot stop the container child; stop it
# explicitly. vLLM 0.26 drains gracefully on SIGTERM.
ExecStop=/usr/bin/podman stop -t 120 frank-primary-glm
# Boot cost: int4 payload page-in plus torch compile/graph capture —
# ~7 min measured 2026-09-30 on a warm page cache, longer cold.
TimeoutStartSec=1800
Restart=on-failure
RestartSec=10

[Install]
WantedBy=multi-user.target