From 59f5474bc718960235b786b07fdf330d93f0d711 Mon Sep 17 00:00:00 2001 From: Vuong Hoang Date: Fri, 25 Sep 2026 14:17:40 -0700 Subject: [PATCH] memory: nh3-ml1 build in progress, blocked on host driver install --- persistent-memory.md | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/persistent-memory.md b/persistent-memory.md index 36168c5..92b634f 100644 --- a/persistent-memory.md +++ b/persistent-memory.md @@ -136,6 +136,15 @@ NH3 DNS are all fine. Open items: `althing-seat-daemon-jekyll` are both disabled (stopped 09-19 and 09-24). The `infra-hermes` handle shows `pull`. +**nh3-ml1 (Prime, 2026-09-25 ~1410): IN PROGRESS.** CT 109 on nh3-pve at +10.100.50.80 (VLAN 50, outside the UDM pool .150–.249), local-zfs, a second +embed/rerank (TEI) backend on the new RTX. Playbooks are host-generic as of +`bc278d4`. **Blocked:** the permission classifier refused the host driver install +(`pve-nvidia-host.yaml` on nh3-pve), and nothing host-side has run. Prime has to +run it or allow it. After it: `gpu-lxc.yaml` with nh3 vars → embed-rerank with +`HOST_NAME/HOST_IP` → parity vs esh-ml1 → monitoring and DNS → gateway routing +(Prime's call). + The pre-shutdown record follows, kept for the next GPU visit: Pre-flight done before shutdown: