Commit Graph
6 Commits
Author SHA1 Message Date
Frank 219a097b39 docs(vault): one page per endpoint, forever -- 45 era pages fold into three
Every payload swap a live endpoint has ever run is now one row in that
endpoint's Eras table, with its rollback path in the same row. No per-attempt
page, no per-swap ledger, nowhere else.

- Added: LLM/frank-archon.md (radiance, 2x R9700 TP=2), LLM/frank-dragoon.md
  (halogen flash-server, 19 eras), LLM/frank-zealot.md (llama.cpp PrismML fork
  on the 3090). Each carries Current shape, Eras, Laws, wire contract, files.
- Deleted: 45 per-payload runbooks -- the frank-dragoon line (11 including the
  pre-name halogen/kingjones/kairic/CIRU/eemin/agentionai/dflash2 pages and the
  benchmark page), the frank-zealot line (llama.cpp/vLLM/ik_llama/SGLang eras),
  the frank-archon line (vLLM/FreeToken/R9V/llama.cpp/radiance eras), plus
  frank-medium, frank-npu and the ubatch/PCIe one-offs that owned nothing.
- Rewired: every wikilink and markdown-path reference to a folded page points
  at the endpoint page instead; the three Research see-also lists and the
  ubatch sweep's runbook link included. No anchored links existed in the set.
- Regenerated both index pages as pure locators -- one row, one clause, no
  numbers -- so the docs_completeness locator law holds for all 153 pages.

tests/docs_completeness.bats green: index links every page, no unresolved
links. The pages moved to .AGENTTRASH/20261018-doc-dedupe/LLM/ (gitignored,
and git history holds every byte).
2026-10-19 00:49:03 -07:00
Frank 55f87fcdce llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot
The 2026-10-09 wire aliases become the service names everywhere:
systemd units, serve scripts, env files and FRANK_* variables,
deploy-plan/deploy-remote service keys, container names, Prometheus
job names + alert rules, Grafana dashboard queries, bats seams,
runbook filenames, homepage/AGENTS lore, and historical prose.
Rollback tags renamed in lockstep. Residue in the tree: zero.
Retired frank-medium/small/npu names are history and stay.

Known casualty: scripts/patches/*.patch context lines were rewritten;
those retired-era vLLM-fork patches no longer apply byte-exact.
2026-10-10 17:03:14 -07:00
Frank f99b698d25 docs(LLM): 3090 worked example — archon w4dn8 methodology ports to GGUF-native quants; 24 GiB size law for 35B-A3B 2026-10-08 23:44:13 -07:00
Frank 757a90057f docs(LLM): recipe portability audit — qwen35moe plugin carries the calibration tap; 35B-A3B w4 fits one R9700 resident 2026-10-08 23:42:58 -07:00
Frank 009e8a885d docs(LLM): Quantization Production — 3090 as the unlocked card (runtime menu, Ampere ceilings, Playbook B safetensors ladder) 2026-10-08 23:38:49 -07:00
Frank 6b677139ad docs(LLM): Quantization Production reference — per-card self-quant playbooks, REAP/Heretic/abliteration/K_P prior art 2026-10-08 22:39:18 -07:00