fix(frank-archon): fold the pinned host pool back to 49,152; keep the 2,048 step
PR #81's pool half measured inert the day it deployed: the 66,560 boot printed the same elastic 26.73 GiB / experts 20.72 / kv cache 5.64 / vram_weights 24.30 as the 49,152 boot and opened the pool with 0 B used, and the qwen38-w5nl64 rig moved vram_kv 269.99 -> 271.25 MiB (window still 7,436 tokens: its 95.37 GiB n-gram table claim decides, not the pool). The step half stays. Tests: 576 ok / 0 fail.
This commit is contained in:
1 parent
ca1475543d
commit
e6fba5d97e
5 files changed
+47
-39
No files matched your search
@@ -170,13 +170,14 @@ fi
|
||||
|
||||
# ONE step size for every mode, quoted from the file that owns it — the audit
|
||||
# law for a radiance rig is to inherit the proven number, not to carry a
|
||||
# campaign-private value: production's FRANK_ARCHON_MAX_BATCHED_TOKENS is 2,048,
|
||||
# the widest step the quantised expert FILE tiers can stream (above it the
|
||||
# engine charges a 10.65 GiB arena to the card and the load refuses), and the
|
||||
# arena it charges comes out of the cache — so the corpora are cut to the window
|
||||
# the boot ledger reports, never the other way round. The 1,024 default this
|
||||
# script carried was PR #80's answer to a starved cache; the pool raise
|
||||
# (frank-archon.env: 66,560 MiB a rank) is the fix, not a narrower step.
|
||||
# campaign-private value: production's FRANK_ARCHON_MAX_BATCHED_TOKENS. The
|
||||
# 1,024 default this script carried was PR #80's answer to a starved cache;
|
||||
# production moved to its widest legal step (2,048) on 2026-10-29 and the rig
|
||||
# follows. The pool raise that shipped with it (66,560 a rank) bought this
|
||||
# container 1.26 MiB of cache (`vram_kv 269.99 -> 271.25 MiB`, window still
|
||||
# 7,436 tokens — the 95.37 GiB n-gram table's claim decides the rig's cache,
|
||||
# not the pool) and was folded back the same day. The corpora stay cut to the
|
||||
# window the boot ledger reports, never the other way round.
|
||||
MNBT="${FRANK_ARCHON_MAX_BATCHED_TOKENS:?FRANK_ARCHON_MAX_BATCHED_TOKENS must be set}"
|
||||
if ! [[ "$MNBT" =~ ^[0-9]+$ ]]; then
|
||||
echo "REFUSED: FRANK_ARCHON_MAX_BATCHED_TOKENS must be a token count (got: $MNBT)" >&2
|
||||
|
||||
Reference in new issue
Block a user