frank-primary: 3 full windows, pool at the contract floor, MNBT 2048

Frank's call 2026-10-01: MAXLEN 262144 x SEQS 3 = 786,432 tokens of contract.
Measured fp8 KV costs 7,698 B/token (4-slot boot 8,311,013,376 B -> 1,079,582
tokens; 5-slot boot 10,388,766,720 B -> 1,350,182 tokens), so the pool floor
for the contract is 6.054e9 B. Pinned at 6,100,000,000 (~792k tokens, ~5.9k
margin) so the remaining ~2.2 GiB versus the 4-slot shape goes to the expert
ARENA - the fork sizes its decode-critical expert cache from the remainder
after weights, pool and workspace.

MNBT 2048 (Frank): the arena sweep measured 6,499 slots at every rung <= 4096,
so the larger batch costs the arena nothing.

Seam retargeted (3 seqs / 6.1e9 / MNBT 2048); docs + AGENTS row + log updated,
including the closed DCP investigation.
This commit is contained in:
Frank committed 2026-10-01 13:25:27 -07:00
1 parent 6bbcaf3999
commit a1b650aabc
5 files changed
+51 -26

No files matched your search

+11
View File
@@ -737,6 +737,17 @@
"Deactivated successfully", and on-failure NEVER fired: the endpoint stayed
down until a human noticed. An explicit `systemctl stop` still wins, so
bench windows and deploys are unaffected.
- **Final shape (Frank's call, 2026-10-01): 3 x 262144, pool at the FLOOR,
MNBT 2048, rest to the arena.** MAXLEN 262144 x SEQS 3 = 786,432 tokens of
contract; measured fp8 costs 7,698 B/token, so 6.054e9 B is the pool floor
and the deployed 6,100,000,000 B leaves a ~5.9k-token margin while handing
the remaining ~2.2 GiB (versus the 4-slot shape) to the expert arena — the
decode-critical cache the fork sizes from the remainder. MNBT 2048 costs the
arena nothing (the sweep measured 6,499 slots at every rung <= 4096).
- **DCP investigated and closed** (see the parallelism survey in the runbook):
`--decode-context-parallel-size 2` is rejected at boot — DCP for GQA requires
TP > the model's KV heads (2), i.e. TP >= 4, i.e. four GPUs. Not a tuning
knob on this box.
- Production bring-up: the shape boots and serves on :7770 — engine log
verified (KV cache size, concurrency, MNBT 1024, gather 32x64) plus live
contract probes (reasoning split, tool_calls). Rollback target for the