docs: record Dankserver VRAM/RAM growth investigation (2026-08-14)

This commit is contained in:
Frank committed 2026-08-14 12:44:24 -07:00
1 parent 9d7643ec5d
commit bea52138d2
3 files changed
+133

No files matched your search

+4
View File
@@ -188,6 +188,10 @@ The user reported that on `frank-default-large` (Dankclaw), a job that is stream
Diagnosis recipe: to tell a client abort from a server release, read the journal around the release time. A client abort shows `W srv stop: cancel task, id_task = N`. A natural stop shows only `slot release` with `truncated = 0` and the final timings line.
### VRAM and RAM growth under load
This crash class recurs on Dankserver. The 2026-08-14 investigation ruled out ctx-checkpoints and ngram-mod as VRAM growth sources and confirmed RAM growth. See [[dankserver-vram-growth]] for the full findings, the monitoring setup, and the mitigation options.
## See Also
- [AGENTS.md](../AGENTS.md) — the git workflow rules