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
servers/fv-ml1/README.md
+1 -1
View File
@@ -182,7 +182,7 @@ embed/rerank/reward trio. GPUs are pinned per container via
**GPU 1 — light / eval / retrieval + char-RP GGUF (~91/98 GB, on-demand):**
> ⚠ **This table is stale (checked 2026-09-27).** Live GPU 1 residents were `scriberr`,
> `vllm-coder`, `vllm-erp-seat` and `vllm-meromero-rp`, plus **`semif`** (:8032, ~8.7 GB resting,
> `vllm-coder`, `vllm-erp-seat` and `vllm-meromero-rp`, plus **`semif`** (**OFFLINE since 2026-09-30, Prime; see `stacks/semif`**; :8032, ~8.7 GB resting when up,
> hard-capped at 12 GiB; `stacks/semif`, since 2026-09-27). Read the host
> (`docker inspect … DeviceRequests`), not this table. (A fixtures-only `augaman` instance ran
> here for about an hour on 2026-09-27 for a speed bench, and was then removed on Prime's call.)