vh/esh-pfi-infrastructure
1
0
Fork 0
Code Issues 7 Pull Requests Actions Packages Projects Releases Wiki Activity

semif: offline by operator ruling — scriberr needs GPU 1 headroom

Browse Source 
Stopped (not removed) 2026-09-30 0135 PT. Scriberr's Parakeet path hardcodes
5-minute slices; attention memory is quadratic in slice length, so a long file
needs >6 GB and hit CUDA OOM with SemIf resident (~6.7 GB free). GPU 1 now
81,806 MiB used. Durable fix (shorter scriberr slices) deferred to later.
This commit is contained in:
vh
2026-09-30 01:36:18 -07:00
parent 5186b3dc9a
commit 9daf43683d
3 changed files with 13 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
stacks/semif/README.md
+10
View File
@@ -1,5 +1,15 @@
# semif
> ⚠ **OFFLINE since 2026-09-30 0135 PT (Prime: "take semif offline for now").** It was
> stopped (`docker compose stop`, NOT removed) to give scriberr its GPU 1 headroom back:
> scriberr's Parakeet path cuts audio into 5-minute slices and needs over 6 GB, and with
> SemIf resident it had ~6.7 GB and hit CUDA OOM on a 35-minute file. Stopping it moved
> GPU 1 from 91,052 to 81,806 MiB used. The image, weights, config and token are all kept;
> `unless-stopped` keeps it down across a reboot. **Do not restart it without Prime's word.**
> To bring it back: `cd /opt/docker/compose/semif && docker compose start`, but first
> make sure scriberr has its room (the durable fix, shortening scriberr's slice length, is
> deferred by Prime to later). Everything below describes the service as it was deployed.
**SemIf option-logit decisions** on **fv-ml1 GPU 1**, the utility card beside
`vllm-coder`, the erp/meromero seats and scriberr. Deployed 2026-09-27 at Prime's
request. Hosting assessment: infra-hermes, 2026-09-25.