From ca2810a319d6c4066d55eb8d67ebb36d38efd55d Mon Sep 17 00:00:00 2001 From: Frank Date: Sun, 27 Sep 2026 22:27:32 -0700 Subject: [PATCH] frank-primary: unit description/notes retuned for the Q8_0 payload --- scripts/frank-primary.service | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/scripts/frank-primary.service b/scripts/frank-primary.service index cd2b0f6..62fee0d 100644 --- a/scripts/frank-primary.service +++ b/scripts/frank-primary.service @@ -1,9 +1,10 @@ -# frank-primary.service — R9V radiance-vLLM endpoint (Qwen3.8-Flash-Next- -# Uncensored IQ4_XS, MTP4, TP=2, tiered experts) on the 2x R9700 pair, -# dankserver :7770. +# 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 196608 window). The +# 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. @@ -17,7 +18,7 @@ # 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-Uncensored IQ4_XS on 2x R9700 +Description=frank-primary — R9V radiance-vLLM Qwen3.8-Flash-Next Q8_0 on 2x R9700 After=network-online.target Wants=network-online.target @@ -34,7 +35,7 @@ ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-primary.sh # 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 ~93 GiB dominates. +# cache; cold (post-reboot) payload page-in of ~175 GiB dominates. TimeoutStartSec=1800 Restart=on-failure RestartSec=10