45 lines
2.1 KiB
Desktop File
45 lines
2.1 KiB
Desktop File
# frank-primary.service — R9V radiance-vLLM endpoint (unsloth
|
|
# Qwen3.8-Flash-Next Q8_0, MTP4, TP=2, tiered experts, 6-shard payload) on
|
|
# the 2x R9700 pair, dankserver :7770. 2026-09-27 cutover from the
|
|
# uncensored IQ4_XS payload (its state dir stays on disk as rollback).
|
|
#
|
|
# Replaces the llama.cpp frank-primary unit (same port, same served alias;
|
|
# harness models.yml unchanged in id, retuned for the 131072 window). The
|
|
# serve script drives the R9V fork's own launcher through the docker->podman
|
|
# shim 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 tiered-expert shape pins tens
|
|
# of GiB of host RAM (the UVA expert host copy plus the 16 GiB PLE pinned
|
|
# reserve). 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 (the shim drives podman as dank).
|
|
[Unit]
|
|
Description=frank-primary — R9V radiance-vLLM Qwen3.8-Flash-Next Q8_0 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-r9v
|
|
# Boot cost: the launcher's preflight doctor (~1 min) after a warm page
|
|
# cache; cold (post-reboot) payload page-in of ~175 GiB dominates.
|
|
TimeoutStartSec=1800
|
|
Restart=on-failure
|
|
RestartSec=10
|
|
|
|
[Install]
|
|
WantedBy=multi-user.target
|