semif: container removed after replacement by intern-decision; rollback is compose up -d

This commit is contained in:
vh
2026-09-30 09:49:30 -07:00
parent 1cf763a7b1
commit 128d1d847c
2 changed files with 12 additions and 6 deletions
+5 -5
View File
@@ -1,21 +1,21 @@
# semif
> ⚠ **REPLACED by intern-decision (Prime, 2026-09-30).** Prime ruled at ~0510 PT: "replace semif
> ⚠ **REPLACED by intern-decision (Prime, 2026-09-30).** Prime ruled that morning: "replace semif
> with intern-decision now". The replacement is `stacks/intern-decision` (Intern-Decision-4B, live since 0941 PT,
> `http://10.251.50.54:8033`, `intern-decision.fv.internal`). It keeps this service's HTTP surface
> (`/decide`, `/decide/shared`, `/health`), so callers only change the URL and the token
> (`secret get intern-decision/api-token`). Its README lists every deliberate difference.
>
> The `semif` container has been **stopped, not removed**, since 0135 PT that day, when it was
> taken offline to give scriberr its GPU 1 headroom back. Its image (`semif-serve:0.1.4`),
> weights, config and token are all kept, and `unless-stopped` keeps it down across a reboot.
> The `semif` container was stopped at 0135 PT that day, to give scriberr its GPU 1 headroom back.
> It was **removed** at 0949 PT (`docker compose down`) so that Homepage stops listing a dead
> tile. The image (`semif-serve:0.1.4`), the weights, this stack's files and the token are all kept.
> Port 8032 and `semif.fv.internal` stay reserved for it.
>
> **Rollback, only on Prime's word.**
> 1. Stop intern-decision first. The two services do not fit GPU 1 together next to scriberr.
> semif held 9.2 GB at rest and peaked at 12.9 GB.
> `cd /opt/docker/compose/intern-decision && docker compose stop`.
> 2. Start semif: `cd /opt/docker/compose/semif && docker compose start`.
> 2. Recreate semif: `cd /opt/docker/compose/semif && docker compose up -d` (the container is removed, so `start` will not work).
> 3. Check nvidia-smi `Free` on GPU 1 against semif's 12.9 GB peak plus scriberr's 5.5 GB (its
> 120 s slices) before calling it done. If it does not cover both, semif collides with scriberr.
>