frank-primary: util 0.90 — production bf16 boot OOM fix

The 0.98 boot died at KV allocation: torch OOM tried 10.28 GiB (the exact
3x262144 bf16 pool = 11,047,010,304 bytes) with 9.46 GiB free per rank.
The rootless bench probe had booted the same numbers; the root unit's
pinned-expert path holds ~0.8 GiB/rank more. Util 0.90 returns ~2.5 GiB/rank
of workspace with the pool ask unchanged; measured KV capacity law
(798,280 tokens at 11.05e9) unchanged.
This commit is contained in:
Frank
2026-10-01 02:12:54 -07:00
parent c1248d4a5d
commit e8524d4046
2 changed files with 14 additions and 9 deletions
+1 -1
View File
@@ -67,4 +67,4 @@ FRANK_PRIMARY_KV_DTYPE=auto
FRANK_PRIMARY_MNBT=1024
FRANK_PRIMARY_GATHER_CHUNKS=32
FRANK_PRIMARY_GATHER_LANES=64
FRANK_PRIMARY_UTIL=0.98
FRANK_PRIMARY_UTIL=0.90