frank-primary + frank-large: export /metrics, raise primary log verbosity to 4

Both b11030 serve scripts never passed --metrics, so /metrics answered
501 and Prometheus could not scrape frank-large (silently down since
its deploy) or frank-primary. frank-primary also gets -lv 4 (VERBOSITY
env tunable, default 4) for the full per-buffer load breakdown.
This commit is contained in:
Frank committed 2026-09-26 20:58:53 -07:00
1 parent bacabdcd49
commit 82ff9dda20
2 files changed
+4

No files matched your search

+1
View File
@@ -81,6 +81,7 @@ ARGS=(
--parallel "$PARALLEL_SLOTS"
--n-gpu-layers 999
--jinja
--metrics
--chat-template-file "$TEMPLATE_FILE"
--chat-template-kwargs '{"preserve_thinking":true}'
--cache-type-k q8_0