Commit Graph
3 Commits
Author SHA1 Message Date
Frank ba2100e22b docs: prefix caching deployed on frank-primary (E8-qualified, 9x/63x reuse TTFT) 2026-09-28 12:33:28 -07:00
Frank f18716563a frank-primary: PLE ready timeout 1800s + bench matrix runbook; index/doc-link fixes
- frank-primary.env: R9V_PLE_READY_TIMEOUT=1800 (PLE registration measured
  740s under page-cache churn; engine default 600s killed a prod boot
  2026-09-28; launch.sh 2de0357 forwards it)
- runbook: prefill/decode bench matrix section (chunk ceiling 4096,
  80-slot policy max, MTP6 3.7x worse, prefix-caching evidence +
  recommendation), fork commit list, residency wording
- index: q8 runbook ACTIVE, uncensored RETIRED (rollback); log entry
  incl. the 9h downtime incident
2026-09-28 10:32:00 -07:00
Frank 671f784ca4 docs: frank-primary q8 cutover — new runbook, uncensored retired as rollback, fleet table/index/log synced 2026-09-27 22:53:19 -07:00