dank/serverAppConfigs
1
0 Fork 0
Code Issues 4 Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request 'feat(frank-archon): four decode slots over a >=700k-token KV pool' (#59) from wt/20261020-213526 into main

Browse Source
This commit was merged in pull request #59.
This commit is contained in:
dank committed 2026-10-20 23:14:35 -07:00
2 parents 31b71a16d6 1bb6399524
commit 7993a336bf
3 files changed
+40 -32
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tests/frank_archon_unit.bats
+7 -4
View File
@@ -145,7 +145,7 @@ nosudo_bin() {
# (torch.compile query_start_loc constraint, 2026-10-02); radiance booted
# seqs 2 in the fp8-native era and the 2026-10-06 sweep had seqs 2 and 3
# tied inside the +-3% noise floor — slots buy concurrency, not speed.
grep -q '^FRANK_ARCHON_MAX_SEQS=2$' "$ENV_FILE"
grep -q '^FRANK_ARCHON_MAX_SEQS=4$' "$ENV_FILE"
grep -q '^FRANK_ARCHON_TP=2$' "$ENV_FILE"
grep -q '^FRANK_ARCHON_TP_WIRE=wht6$' "$ENV_FILE"
grep -q '^FRANK_ARCHON_SPEC_TOKENS=2$' "$ENV_FILE"
@@ -158,7 +158,7 @@ nosudo_bin() {
# so the pool's token count is a boot-ledger line — verified live by the
# capacity leg of scripts/probe-frank-archon-kv.py at every cutover.
grep -q '^FRANK_ARCHON_PLACEMENT=expert_tiered$' "$ENV_FILE"
grep -q '^FRANK_ARCHON_HOST_POOL_MIB=44928$' "$ENV_FILE"
grep -q '^FRANK_ARCHON_HOST_POOL_MIB=49152$' "$ENV_FILE"
grep -q '^FRANK_ARCHON_KV_DTYPE=fp8$' "$ENV_FILE"
grep -q '^FRANK_ARCHON_NGRAM_PLACEMENT=ram$' "$ENV_FILE"
# Prefix cache: pinned host RAM only (the disk tier was removed), and the
@@ -177,8 +177,11 @@ nosudo_bin() {
[ "$ttmt" -gt "$ttmm" ]
pool=$(awk -F= '/^FRANK_ARCHON_HOST_POOL_MIB=/{print $2}' "$ENV_FILE")
ph=$(awk -F= '/^FRANK_ARCHON_PREFIX_CACHE_MIB=/{print $2}' "$ENV_FILE")
# 2 pools + PLE 47.7 GiB (48,824 MiB) + prefix host, rounded up.
ledger=$(( 2 * pool + 48824 + ph + 2048 ))
# 2 pools + PLE 47.7 GiB (48,824 MiB) + prefix host + MNBT + the auto
# checkpoint store (MAX_SEQS x 10 slots of 112 MiB -- the store is pinned host
# memory too, and it grows with the slot count).
seqs=$(awk -F= '/^FRANK_ARCHON_MAX_SEQS=/{print $2}' "$ENV_FILE")
ledger=$(( 2 * pool + 48824 + ph + 2048 + seqs * 10 * 112 ))
[ "$ttmm" -ge "$ledger" ]
# The .rad size floor is positive (a truncated convert must fail fast).
grep -q '^FRANK_ARCHON_RAD_MIN_MIB=' "$ENV_FILE"