fix(scriberr-rebuild): memory stage works on a shared GPU 3

Scriberr moved to fv-ml1 GPU 3 on 2026-09-30, so the card is no longer idle when the rebuild runs. The memory stage now requires >= 20 GB free instead of an idle card (GPUs 0-2 still fail that) and attributes the peak only to the host PIDs of its own container, captured with docker top alongside the 0.2 s nvidia-smi samples. Verified with five processes on the card: peak 5,496 MiB, identical to the exclusive-card figure.
2026-09-30 13:30:29 -07:00
parent e3dbb08d84
commit 92501a29c1
2 changed files with 22 additions and 15 deletions
@@ -115,7 +115,7 @@ It clones that sha into a new `/opt/docker/src/scriberr-<sha7>-<suffix>`,
 `git apply --check`s each patch (a conflict stops the run and names the patch),
 builds `scriberr:local-blackwell-<sha7>-<suffix>` without touching older tags,
 then runs the embed, unit, seam and memory stages and prints a PASS/FAIL table.
-Memory runs on GPU 3 and refuses a GPU that is not idle. A conflict means the
+Memory runs on GPU 3, which Scriberr itself now occupies (2026-09-30); the stage needs ≥ 20 GB free and counts only its own container's PIDs, so a Scriberr job on the card neither blocks nor pollutes it. A conflict means the
 patch needs rebasing: in a checkout of the new sha, `git am -3` the old patch,
 resolve, run the unit tests, then `git format-patch -1 --stdout >
 0001-parakeet-pause-aware-slicer.patch` and re-run the rebuild.