frank-large: record deployed boot facts (pool 819,332 tokens, 3.13x, 230 s)

Live battery green after deploy #3: alias, reasoning split into `reasoning`, tool_calls, /metrics acceptance pos0 69% pos1 44% - the cross-model MTP head performs as measured in the bench window.
2026-10-01 19:48:56 -07:00
parent 780c307354
commit 3c339eeba2
2 changed files with 10 additions and 2 deletions
@@ -72,6 +72,9 @@ FRANK_LARGE_PUBLISH=7770:7770
 FRANK_LARGE_MAXLEN=262144
 FRANK_LARGE_SEQS=4
 FRANK_LARGE_UTIL=0.45
+# First-deploy boot (2026-10-01): GPU KV cache size 819,332 tokens,
+# Maximum concurrency for 262,144 tokens per request 3.13x; healthy at 230 s.
+# Change MAXLEN/SEQS/UTIL or the image and this line moves — re-read it.

 # --- speculative decode: cross-model MTP (measured +51% decode) ---------------
 # mtp beats dflash here (19.8 vs 17.4 t/s) and needs 2 draft tokens, not 8: